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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that indicate a contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Despite"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esian
    -0.71
    ISE
    -0.69
    lees
    -0.69
    ecycle
    -0.67
    uci
    -0.65
    enter
    -0.65
    taboola
    -0.65
    aim
    -0.63
    isa
    -0.63
    ahime
    -0.63
    POSITIVE LOGITS
     acknowledging
    0.70
     Victory
    0.68
    ĸļ
    0.68
    imaru
    0.67
     spite
    0.67
    SourceFile
    0.66
    mble
    0.63
    pite
    0.63
     stating
    0.62
     knowing
    0.61
    Act Density 0.015%

    No Known Activations