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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing action or movement

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with action or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortunately
    -0.71
    deal
    -0.67
    tel
    -0.63
    onsense
    -0.62
    gui
    -0.62
    bal
    -0.61
    76561
    -0.61
    ont
    -0.61
     attaching
    -0.59
    croft
    -0.58
    POSITIVE LOGITS
    iaries
    0.68
    HAM
    0.66
     hay
    0.65
    iary
    0.65
    Ni
    0.59
    oji
    0.59
    AME
    0.58
     cough
    0.57
    ersed
    0.56
     stale
    0.56
    Act Density 0.272%

    No Known Activations