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

    Neuronpedia

    INDEX
    Explanations

    situations where someone decides something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of understanding or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.81
    kers
    -0.74
    por
    -0.72
    nor
    -0.71
    sole
    -0.67
    wcsstore
    -0.66
    ãĥĨãĤ£
    -0.65
     refusal
    -0.64
    ankind
    -0.64
    interrupted
    -0.63
    POSITIVE LOGITS
    sonian
    1.01
     figured
    0.98
    OTAL
    0.72
    ISC
    0.70
    uling
    0.69
     prominently
    0.67
    åĤ
    0.65
    lio
    0.65
     Logic
    0.64
    iculty
    0.63
    Act Density 0.008%

    No Known Activations