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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events being done or undertaken

    oai_token-act-pair · gpt-3.5-turbo

    formal or sophisticated terms related to actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verbs
    -0.82
    paren
    -0.69
    elling
    -0.69
    parse
    -0.68
    ammy
    -0.66
    bind
    -0.65
    ramid
    -0.63
    fire
    -0.62
    acea
    -0.62
    Cop
    -0.61
    POSITIVE LOGITS
    ments
    0.94
    orld
    0.74
    hower
    0.73
    chnology
    0.72
     hast
    0.69
     therein
    0.68
    ngth
    0.67
     Presents
    0.67
    ment
    0.66
    wcsstore
    0.65
    Act Density 0.373%

    No Known Activations