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

    Neuronpedia

    INDEX
    Explanations

    statistical figures and percentages related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.67
     Pengu
    -0.60
     separat
    -0.59
     worshipped
    -0.57
    vana
    -0.55
    agara
    -0.55
    liga
    -0.54
     ling
    -0.54
    orno
    -0.54
    oided
    -0.54
    POSITIVE LOGITS
    %.
    1.10
    %,
    0.91
    %"
    0.91
     leaps
    0.89
    dB
    0.89
    %;
    0.84
     percent
    0.78
     margin
    0.77
     percentage
    0.76
     dB
    0.76
    Act Density 0.047%

    No Known Activations