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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or quantity of entities or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sport
    -0.72
    AIDS
    -0.70
    ira
    -0.69
    soType
    -0.66
    dad
    -0.66
    inition
    -0.64
    bringer
    -0.63
    pal
    -0.63
    elsius
    -0.62
     traged
    -0.62
    POSITIVE LOGITS
     several
    0.89
     three
    0.87
     four
    0.85
     five
    0.83
     varying
    0.82
     multiple
    0.82
     two
    0.81
     seven
    0.81
     dots
    0.80
     six
    0.79
    Act Density 0.040%

    No Known Activations