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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences that provide instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.84
     earthqu
    -0.74
    ĸļ士
    -0.74
     depl
    -0.71
    Þ
    -0.71
     exting
    -0.70
     volunte
    -0.69
     therap
    -0.68
     dogged
    -0.68
     pione
    -0.68
    POSITIVE LOGITS
     Ideally
    1.28
     Usually
    1.26
     Typically
    1.20
     Meaning
    1.20
     Suppose
    1.19
     Generally
    1.18
     Specifically
    1.17
     Personally
    1.15
     Normally
    1.13
     Otherwise
    1.11
    Act Density 0.418%

    No Known Activations