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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something as a testament or evidence of some quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying strong validation or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -1.06
    cloth
    -0.89
    thia
    -0.70
     oats
    -0.68
    croft
    -0.68
    cliffe
    -0.66
    waves
    -0.66
    FP
    -0.65
    yip
    -0.63
    hands
    -0.60
    POSITIVE LOGITS
    arily
    1.00
    ments
    0.95
    orio
    0.88
    alist
    0.84
    ary
    0.83
    antly
    0.82
    arist
    0.79
    ificant
    0.79
    arium
    0.78
    iary
    0.78
    Act Density 0.046%

    No Known Activations