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

    Neuronpedia

    INDEX
    Explanations

    the word "guess" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    import
    -0.73
    affer
    -0.68
    loader
    -0.67
    Rated
    -0.65
    blance
    -0.65
    orer
    -0.64
    RAW
    -0.64
    iqueness
    -0.64
    erer
    -0.63
    è¦ļéĨĴ
    -0.63
    POSITIVE LOGITS
     unsurprisingly
    0.66
     JC
    0.64
     sarc
    0.63
     goodbye
    0.63
     it
    0.62
     ironic
    0.60
     MI
    0.60
     glad
    0.59
    rh
    0.59
    tera
    0.58
    Act Density 0.029%

    No Known Activations