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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deaux
    -0.15
    çĮ®
    -0.14
    .Unity
    -0.14
    UNET
    -0.14
     PURE
    -0.13
    аÑĩе
    -0.13
    Violation
    -0.13
    _Util
    -0.13
    ugs
    -0.13
    ledon
    -0.13
    POSITIVE LOGITS
     confirm
    0.54
     confirmed
    0.54
     confirmation
    0.52
    confirmed
    0.50
    confirm
    0.49
     Confirm
    0.49
     CONF
    0.49
    Confirm
    0.48
     Conf
    0.48
    -confirm
    0.48
    Act Density 0.245%

    No Known Activations