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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating some form of removal, reversal, or suspension

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the cessation or reversal of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.70
    resents
    -0.62
    acion
    -0.61
    idth
    -0.61
    Fit
    -0.60
    ocl
    -0.59
    dom
    -0.59
    sit
    -0.58
    ipeg
    -0.58
    Pr
    -0.58
    POSITIVE LOGITS
     by
    0.84
     aback
    0.73
     entirely
    0.69
     BY
    0.67
    livious
    0.66
    ĸļ
    0.65
    oing
    0.64
     proport
    0.64
     accordingly
    0.63
     unanimously
    0.62
    Act Density 0.262%

    No Known Activations