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

    Neuronpedia

    INDEX
    Explanations

    words related to paralysis or being disabled

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "par" indicating parallelism or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.88
    éĹĺ
    -0.76
    ¥µ
    -0.76
    OME
    -0.74
    andestine
    -0.73
    hower
    -0.73
    hirt
    -0.71
    士
    -0.70
    ELD
    -0.70
     Carbuncle
    -0.70
    POSITIVE LOGITS
    rot
    1.02
    allel
    1.01
    amount
    0.94
    ietal
    0.93
    icularly
    0.91
    rots
    0.90
    ison
    0.89
    abolic
    0.89
    icy
    0.84
    sec
    0.83
    Act Density 0.010%

    No Known Activations