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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desires or preferences for specific options

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

    something differentcloser tocarry a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.48
    УДК
    -0.45
     auroit
    -0.42
    enterOuterAlt
    -0.41
     étoit
    -0.40
     kautta
    -0.40
    aarrggbb
    -0.39
    Datuak
    -0.39
    AsyncResult
    -0.39
     feroit
    -0.39
    POSITIVE LOGITS
     foothold
    0.44
     haircut
    0.42
    jobb
    0.41
    ніципалі
    0.41
    specifically
    0.41
     específico
    0.40
    
    0.39
     grieve
    0.39
     hoped
    0.39
    BeginContext
    0.37
    Act Density 0.023%

    No Known Activations