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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal narratives involving distressing experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    atform
    -1.18
    Published
    -1.17
    acia
    -1.17
    abet
    -1.14
    olin
    -1.07
    obook
    -1.06
    ulty
    -1.03
    ilogy
    -1.02
    Ô
    -1.01
    ilic
    -1.00
    POSITIVE LOGITS
    lihood
    1.74
    lier
    1.42
     hers
    1.15
     ours
    1.09
     yours
    1.02
    liest
    1.01
     wildfire
    1.00
     theirs
    0.98
     drafts
    0.94
    liness
    0.91
    Act Density 1.329%

    No Known Activations