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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to audio processing

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of a specific suffix related to a name or indication of ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.66
    pled
    -0.66
     Amos
    -0.64
    ctica
    -0.64
    ACTED
    -0.63
    ¥µ
    -0.63
    cible
    -0.61
    istor
    -0.59
    ©¶æ
    -0.59
     altar
    -0.59
    POSITIVE LOGITS
    keye
    0.92
    rome
    0.91
    sburgh
    0.83
    ynski
    0.83
    onne
    0.83
    icago
    0.83
    sen
    0.82
    mann
    0.81
    ards
    0.81
    olas
    0.81
    Act Density 0.014%

    No Known Activations