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

    Neuronpedia

    INDEX
    Explanations

    directive phrases prompting action or advice

    oai_token-act-pair · gpt-3.5-turbo

    the verb 'be' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regation
    -0.67
     Osc
    -0.67
     viz
    -0.66
    regate
    -0.64
    PsyNetMessage
    -0.63
     ILCS
    -0.62
    --+
    -0.59
    kHz
    -0.58
    âĨij
    -0.56
     Sr
    -0.55
    POSITIVE LOGITS
     careful
    1.19
     sure
    1.17
    gins
    1.12
     aware
    1.11
    yond
    1.10
    ijing
    1.10
     wary
    1.07
    hemoth
    1.06
     warned
    1.05
    acons
    1.04
    Act Density 0.051%

    No Known Activations