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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer science and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to Game Score metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ications
    -0.82
    icating
    -0.74
    landish
    -0.73
    swick
    -0.71
    ted
    -0.71
    jad
    -0.70
    aneously
    -0.69
    icative
    -0.69
    issance
    -0.66
    acles
    -0.65
    POSITIVE LOGITS
    earch
    0.98
    IFT
    0.92
    ngth
    0.78
    ESSION
    0.75
    leep
    0.75
    ORGE
    0.75
    GS
    0.74
    OURCE
    0.74
    YS
    0.72
    avage
    0.72
    Act Density 0.023%

    No Known Activations