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

    Neuronpedia

    INDEX
    Explanations

    items that can physically fit together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compatibility or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipl
    -0.72
    clips
    -0.70
    ä¼
    -0.65
    iolet
    -0.62
    externalActionCode
    -0.59
    violent
    -0.59
    theless
    -0.58
    aiden
    -0.57
    perty
    -0.57
    ãĥ£
    -0.57
    POSITIVE LOGITS
     fit
    0.97
    MENTS
    0.95
    nah
    0.84
    gerald
    0.83
     fits
    0.81
     snug
    0.77
     Fit
    0.77
    ters
    0.76
     fitting
    0.75
    fit
    0.73
    Act Density 0.011%

    No Known Activations