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

    Neuronpedia

    INDEX
    Explanations

    personal names

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Andrey."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ided
    -0.72
     motto
    -0.71
     periodic
    -0.69
    İĭ
    -0.67
    pmwiki
    -0.65
    OPS
    -0.64
     perpetual
    -0.64
    Offline
    -0.63
     poignant
    -0.61
     occasional
    -0.61
    POSITIVE LOGITS
    rey
    1.25
    leigh
    0.84
    reys
    0.82
    eta
    0.82
    bill
    0.81
    interstitial
    0.81
    alez
    0.80
    berg
    0.80
    borg
    0.80
    hawks
    0.79
    Act Density 0.005%

    No Known Activations