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

    Neuronpedia

    INDEX
    Explanations

    specific instances or examples of something being the only one of its kind

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing uniqueness or the exclusive nature of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptic
    -0.68
    des
    -0.67
    rawl
    -0.65
    ategor
    -0.65
    md
    -0.65
    iety
    -0.64
    elist
    -0.64
    ends
    -0.63
     Carbuncle
    -0.61
    kins
    -0.60
    POSITIVE LOGITS
     thing
    0.94
     obstacle
    0.84
     conceivable
    0.83
     surviving
    0.82
     drawback
    0.81
     logical
    0.78
     remaining
    0.77
     reason
    0.76
     exception
    0.74
     beneficiary
    0.74
    Act Density 0.027%

    No Known Activations