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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.75
     princ
    -0.72
    ensical
    -0.68
     enthusi
    -0.68
    acebook
    -0.67
     exha
    -0.65
    anwhile
    -0.65
     mathemat
    -0.63
    ��
    -0.63
    humans
    -0.63
    POSITIVE LOGITS
    't
    1.21
    ´
    0.94
    ned
    0.79
    ¢
    0.74
    "}],"
    0.72
    �
    0.70
    és
    0.67
    gered
    0.66
    �
    0.66
    `
    0.66
    Act Density 0.074%

    No Known Activations