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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the publication and posting of articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meric
    -0.71
     frankly
    -0.65
     nonetheless
    -0.64
    lov
    -0.64
     constantly
    -0.63
    asty
    -0.61
     variety
    -0.61
    tools
    -0.58
    like
    -0.58
     turnaround
    -0.57
    POSITIVE LOGITS
     Te
    0.71
    INGTON
    0.69
    Micro
    0.68
    hip
    0.65
     Alto
    0.64
    Published
    0.64
    poon
    0.64
    YP
    0.63
     McGr
    0.63
    ghan
    0.63
    Act Density 0.092%

    No Known Activations