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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and evaluating options

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

    before verbs or punctuation

    np_acts-logits-general · gemini-2.0-flash

    verb followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.39
     Jefus
    -1.33
    ſelf
    -1.32
     Majefty
    -1.30
    ſelves
    -1.29
     Houſe
    -1.27
     houſe
    -1.19
     Efq
    -1.19
     Diſ
    -1.19
     purpoſe
    -1.19
    POSITIVE LOGITS
    …
    0.72
     …
    0.68
     a
    0.67
     
    0.66
     to
    0.64
     in
    0.63
     en
    0.62
     of
    0.62
    …”
    0.61
    ...
    0.59
    Act Density 0.280%

    No Known Activations