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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and statistics, particularly when related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    key statistics and attributes related to various entities and subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARD
    -0.92
    advertising
    -0.83
    UE
    -0.69
    HAEL
    -0.67
     Digest
    -0.66
    ARC
    -0.65
    ACA
    -0.63
    });
    -0.63
    jen
    -0.62
    Ĥİ
    -0.62
    POSITIVE LOGITS
     knack
    0.99
    been
    0.98
    kees
    0.86
     figured
    0.84
     lined
    0.81
     flair
    0.78
     installed
    0.77
    ointed
    0.76
     fetish
    0.71
     capability
    0.69
    Act Density 0.953%

    No Known Activations