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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -ons
    -0.16
    IRMWARE
    -0.16
    zcze
    -0.15
    <?,
    -0.15
    ukt
    -0.14
    sdale
    -0.14
    weit
    -0.14
    ksam
    -0.14
    gaard
    -0.14
    dera
    -0.14
    POSITIVE LOGITS
    /or
    0.19
     Bust
    0.16
    /th
    0.15
    reu
    0.15
    rog
    0.15
    alous
    0.15
    ehr
    0.15
    adel
    0.15
     Rebel
    0.14
    iali
    0.14
    Act Density 0.064%

    No Known Activations