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

    Neuronpedia

    INDEX
    Explanations

    words related to code formatting and special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or encoding artifacts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oidal
    -0.88
    oids
    -0.87
    oid
    -0.76
    apsed
    -0.76
    dfx
    -0.71
    ppelin
    -0.67
    APS
    -0.66
    idious
    -0.65
    etsk
    -0.64
     liner
    -0.64
    POSITIVE LOGITS
    âĤ¬
    1.30
    tre
    0.98
    tel
    0.96
    ternity
    0.90
    ¯
    0.90
    ´
    0.89
    ©
    0.88
    ¯¯
    0.87
    ··
    0.85
    ¯¯¯¯
    0.84
    Act Density 0.030%

    No Known Activations