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

    Neuronpedia

    INDEX
    Explanations

    verbs related to social interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    interactions or conflicts between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aroo
    -0.72
    unction
    -0.70
    wcs
    -0.66
    lot
    -0.66
    roma
    -0.66
    adier
    -0.64
    videos
    -0.63
    learn
    -0.62
    marine
    -0.59
    levard
    -0.58
    POSITIVE LOGITS
     each
    2.23
    each
    1.76
     Each
    1.46
     apiece
    1.44
    Each
    1.32
     one
    1.00
     themselves
    0.92
     another
    0.84
    selves
    0.80
     respective
    0.79
    Act Density 0.391%

    No Known Activations