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

    Neuronpedia

    INDEX
    Explanations

    descriptions of technical procedures or guides

    oai_token-act-pair · gpt-3.5-turbo

    practical instructions and guidance for tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.70
    cffffcc
    -0.64
    )."
    -0.61
     Pwr
    -0.59
    >[
    -0.58
    )?
    -0.56
    );
    -0.55
    nob
    -0.55
    tch
    -0.54
    robat
    -0.53
    POSITIVE LOGITS
     misconceptions
    0.60
     Adin
    0.59
     NX
    0.54
     Gateway
    0.54
    asca
    0.54
     vex
    0.53
     informative
    0.53
     encount
    0.52
     investig
    0.52
     SEM
    0.52
    Act Density 1.617%

    No Known Activations