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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to accumulation and value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ
    -0.67
    .","
    -0.66
    .''
    -0.65
    \.
    -0.60
    "},"
    -0.58
    `.
    -0.58
    .�
    -0.57
    ''.
    -0.57
    /
    -0.56
    .'
    -0.55
    POSITIVE LOGITS
    ensibly
    0.73
     thereto
    0.70
     afterwards
    0.70
    later
    0.69
     "$:/
    0.66
     to
    0.65
     onward
    0.65
     incidentally
    0.64
     later
    0.63
     onwards
    0.62
    Act Density 0.754%

    No Known Activations