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

    Neuronpedia

    INDEX
    Explanations

    the concatenation sequence 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to cooking and food experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cent
    -0.60
    heit
    -0.60
    abouts
    -0.58
     consulate
    -0.57
    ajor
    -0.57
     intended
    -0.56
    ijing
    -0.56
    resso
    -0.55
    erville
    -0.54
    agy
    -0.54
    POSITIVE LOGITS
    âĵĺ
    0.73
    ONSORED
    0.72
    ?????-
    0.69
    CONCLUS
    0.68
    Especially
    0.67
    Example
    0.67
    Examples
    0.65
    gencies
    0.64
    Therefore
    0.63
    potion
    0.62
    Act Density 0.508%

    No Known Activations