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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis indicating a large quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.85
    etts
    -0.84
    ĺħ
    -0.80
    grad
    -0.76
    ologies
    -0.73
    jac
    -0.70
    oway
    -0.70
    bley
    -0.69
    Ń·
    -0.68
    sov
    -0.67
    POSITIVE LOGITS
     ado
    0.76
     effort
    0.73
     appreciated
    0.71
     attention
    0.69
    antz
    0.66
     interest
    0.64
     faith
    0.64
     integrity
    0.63
    EAR
    0.63
     conscience
    0.62
    Act Density 0.022%

    No Known Activations