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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prompt or immediate action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating immediacy or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.79
    lain
    -0.75
    edom
    -0.75
    ammy
    -0.75
    obal
    -0.73
    gerald
    -0.73
    adr
    -0.73
    alg
    -0.72
     skelet
    -0.72
    tty
    -0.72
    POSITIVE LOGITS
    aneously
    0.92
    Introduced
    0.86
     Toro
    0.63
     thereafter
    0.62
     Ukrainian
    0.62
     afterwards
    0.62
     followed
    0.61
     glance
    0.61
     before
    0.60
     Ig
    0.60
    Act Density 0.039%

    No Known Activations