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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åİ
    -0.77
    ITED
    -0.76
    ãĥ«
    -0.70
    kefeller
    -0.69
    ãĥ¤
    -0.66
    ¯¯¯¯¯¯¯¯
    -0.66
     obser
    -0.65
     detrim
    -0.65
    IRT
    -0.64
    pload
    -0.64
    POSITIVE LOGITS
    xual
    0.85
    cake
    0.85
    iles
    0.80
    imet
    0.76
    imeter
    0.74
     ABV
    0.71
    uary
    0.69
    rated
    0.68
     annual
    0.68
    percent
    0.68
    Act Density 0.058%

    No Known Activations