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

    Neuronpedia

    INDEX
    Explanations

    negative or critical comments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.80
    MAT
    -0.67
    alez
    -0.66
    mut
    -0.64
    hang
    -0.63
    eki
    -0.63
    emetery
    -0.63
    iom
    -0.62
    runs
    -0.62
    ulative
    -0.62
    POSITIVE LOGITS
     percept
    0.88
     bother
    0.76
     noticeable
    0.73
    withstanding
    0.73
     bothered
    0.71
     ever
    0.70
     paralle
    0.70
     distinguish
    0.70
     insignificant
    0.70
     shy
    0.69
    Act Density 0.009%

    No Known Activations