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

    Neuronpedia

    INDEX
    Explanations

    questions related to business practices and economic outcomes

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

    Follows punctuation then opinion/conjunction

    np_acts-logits-general · gemini-2.0-flash

    sentence separators and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deſt
    -0.80
     iſt
    -0.77
     ſur
    -0.77
     itſelf
    -0.77
    !’
    -0.76
     whoſe
    -0.73
    tvguidetime
    -0.73
     ſta
    -0.72
    ,’”
    -0.72
     becauſe
    -0.71
    POSITIVE LOGITS
     IIRC
    1.02
    IMHO
    0.88
     IMHO
    0.86
     iirc
    0.84
     IMO
    0.83
     pretty
    0.78
     I
    0.76
    FWIW
    0.70
     Basically
    0.70
     basically
    0.69
    Act Density 0.618%

    No Known Activations