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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or advancements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to new developments or introductions of concepts and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paran
    -0.63
     throats
    -0.59
     bra
    -0.59
    uba
    -0.57
    soever
    -0.57
    sb
    -0.56
    md
    -0.56
     blat
    -0.56
     vomit
    -0.55
    Interested
    -0.54
    POSITIVE LOGITS
     thereof
    0.97
     of
    0.92
     date
    0.79
     OF
    0.77
    date
    0.76
    itious
    0.74
    idable
    0.73
    uation
    0.73
    rite
    0.71
    of
    0.71
    Act Density 0.148%

    No Known Activations