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

    Neuronpedia

    INDEX
    Explanations

    contradictions or opposing statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "yet" indicating contrast or concession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rities
    -0.77
    edu
    -0.76
    tein
    -0.70
    ancial
    -0.68
    gang
    -0.66
    ussions
    -0.63
    Times
    -0.63
    Chicken
    -0.63
    puters
    -0.62
    cases
    -0.62
    POSITIVE LOGITS
     somehow
    0.97
     mirac
    0.78
     behold
    0.78
     inexpl
    0.74
     strangely
    0.73
    heric
    0.73
    tons
    0.71
    chart
    0.69
     somew
    0.69
     again
    0.68
    Act Density 0.024%

    No Known Activations