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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and statistical information related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WordPress
    -0.57
    iannopoulos
    -0.53
     unparalleled
    -0.53
     shale
    -0.52
     fracking
    -0.50
     spew
    -0.49
     relatively
    -0.48
     nonviolent
    -0.48
     safely
    -0.48
     benchmark
    -0.48
    POSITIVE LOGITS
    /-
    0.75
     Ago
    0.68
     denotes
    0.68
    _>
    0.68
    quished
    0.67
    cellaneous
    0.65
    ãĤ´ãĥ³
    0.65
    ?]
    0.62
     Leilan
    0.62
     ?)
    0.61
    Act Density 0.948%

    No Known Activations