Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of selection or identification processes related to candidates or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Alternatives, options, or multiple choices

    np_acts-logits-general · gemini-2.0-flash

    multiple options or candidates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.55
    DeleteBehavior
    -0.37
     secr
    -0.36
     stylo
    -0.35
     jugu
    -0.33
     secreta
    -0.32
     Harcourt
    -0.32
    turnstile
    -0.32
     Wicidata
    -0.32
     Públicas
    -0.31
    POSITIVE LOGITS
     alternatives
    0.66
     candidates
    0.59
    alternatives
    0.57
     options
    0.56
     competing
    0.55
    Alternatives
    0.55
     vying
    0.55
    options
    0.54
     Alternatives
    0.54
    candidates
    0.52
    Act Density 0.606%

    No Known Activations