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

    Neuronpedia

    INDEX
    Explanations

    references to undergoing various tests, procedures, evaluations, or changes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "undergo" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wi
    -0.84
    rug
    -0.66
    ****************
    -0.65
    AW
    -0.63
    cube
    -0.62
    mob
    -0.62
    lord
    -0.59
     Indies
    -0.58
     Liberals
    -0.58
    spir
    -0.58
    POSITIVE LOGITS
     undergone
    1.03
    uberty
    0.91
     undergo
    0.90
    uates
    0.82
     surgery
    0.81
    ospital
    0.79
    veyard
    0.78
    metic
    0.76
     transformations
    0.76
    ived
    0.76
    Act Density 0.022%

    No Known Activations