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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical attributes or support

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to support, potential, and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adow
    -0.72
    edIn
    -0.67
    batch
    -0.65
    haps
    -0.63
    outube
    -0.61
    hoff
    -0.60
     Despair
    -0.59
    TAIN
    -0.58
    Release
    -0.57
    Represent
    -0.57
    POSITIVE LOGITS
    liest
    1.28
    iest
    1.13
     equivalent
    1.03
    est
    0.87
    same
    0.87
    erity
    0.81
    hest
    0.80
     necessary
    0.79
     requisite
    0.78
     easiest
    0.74
    Act Density 0.411%

    No Known Activations