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

    Neuronpedia

    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "It’s" followed by various contexts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ={
    -0.64
    scope
    -0.63
    andise
    -0.63
    rence
    -0.62
    INST
    -0.62
    ESE
    -0.60
    igraph
    -0.59
     Deaths
    -0.59
    umbnail
    -0.59
    911
    -0.59
    POSITIVE LOGITS
     gonna
    1.10
     gotta
    1.09
     been
    0.99
     unclear
    0.98
     got
    0.91
     impossible
    0.88
     gotten
    0.87
     easy
    0.86
     worth
    0.84
     easier
    0.83
    Act Density 0.075%

    No Known Activations