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

    Neuronpedia

    INDEX
    Explanations

    words related to supernatural or extraordinary concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pigeon
    -0.82
     targeted
    -0.82
     relative
    -0.74
     clitor
    -0.73
     flying
    -0.72
     envelope
    -0.72
     pickup
    -0.70
     favor
    -0.69
     barg
    -0.69
     mount
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.41
    ternity
    0.97
    ï¸
    0.96
    However
    0.95
    uthor
    0.95
    \/\/
    0.94
    ICE
    0.93
    Therefore
    0.92
    ¯¯
    0.92
    conom
    0.89
    Act Density 0.126%

    No Known Activations