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

    Neuronpedia

    INDEX
    Explanations

    phrases related to caution and concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts related to entrapment or vulnerability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsky
    -0.79
    miah
    -0.69
    gres
    -0.68
    inas
    -0.68
    tsy
    -0.67
    thood
    -0.67
    iami
    -0.65
    aru
    -0.64
    kins
    -0.64
    eva
    -0.63
    POSITIVE LOGITS
     albeit
    1.26
     akin
    1.24
    albeit
    1.11
     devoid
    0.97
     requiring
    0.93
     reminiscent
    0.91
     worthy
    0.90
     whereby
    0.88
     consisting
    0.87
     wherein
    0.86
    Act Density 0.371%

    No Known Activations