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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to counting and numerical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obser
    -0.71
     misunder
    -0.69
     Harbor
    -0.67
     conditioning
    -0.63
     constitu
    -0.62
    insula
    -0.61
     educ
    -0.60
     Goods
    -0.59
    SPONSORED
    -0.59
     appre
    -0.59
    POSITIVE LOGITS
    enance
    1.82
    downs
    0.92
    oleon
    0.78
     calories
    0.76
    ENCY
    0.76
    rified
    0.75
    down
    0.73
    omp
    0.70
    rows
    0.69
    antine
    0.68
    Act Density 0.011%

    No Known Activations