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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly names associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rers
    -0.80
    cru
    -0.76
    bre
    -0.76
    rum
    -0.76
    pole
    -0.72
    quickShipAvailable
    -0.71
    shape
    -0.70
    wolves
    -0.70
    pine
    -0.69
    rer
    -0.69
    POSITIVE LOGITS
    osit
    0.94
    wana
    0.87
    oser
    0.83
    osate
    0.82
    ylon
    0.80
    oba
    0.78
    nect
    0.74
    ĺħ
    0.74
    itton
    0.73
    ça
    0.73
    Act Density 0.028%

    No Known Activations