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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and personal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ics
    -0.14
     åı
    -0.14
    ods
    -0.14
     Avery
    -0.14
    436
    -0.13
     Val
    -0.13
    594
    -0.13
     Bond
    -0.13
     Viol
    -0.13
    inee
    -0.13
    POSITIVE LOGITS
    asto
    0.15
    .gms
    0.15
    _ioctl
    0.15
    лиÑĪком
    0.15
    Touches
    0.14
    SizeMode
    0.14
     NONINFRINGEMENT
    0.14
    elivery
    0.14
    kart
    0.14
    ëįķ
    0.14
    Act Density 1.050%

    No Known Activations