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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a necessity or recommendation

    oai_token-act-pair · gpt-3.5-turbo

    references to the necessity for action or change in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ank
    -0.56
    theless
    -0.56
     Surv
    -0.54
     VERS
    -0.52
     Petra
    -0.52
     vag
    -0.51
     choir
    -0.50
     prest
    -0.49
     beans
    -0.49
     livest
    -0.49
    POSITIVE LOGITS
     to
    1.09
     for
    1.05
    lessly
    0.96
    for
    0.90
    lest
    0.88
    to
    0.85
    reprene
    0.82
    iness
    0.80
    To
    0.72
    ozy
    0.71
    Act Density 0.104%

    No Known Activations