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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ought
    -0.16
    plen
    -0.16
    aven
    -0.15
     Vz
    -0.14
    anik
    -0.14
    lenen
    -0.14
     thanks
    -0.14
    357
    -0.14
    complexContent
    -0.14
    otos
    -0.14
    POSITIVE LOGITS
     Alexand
    0.15
    strcasecmp
    0.14
    оди
    0.14
    ãĤ·ãĤ§
    0.14
    κι
    0.14
    ry
    0.14
    лекÑģанд
    0.14
     Scarlet
    0.14
    elu
    0.14
     wake
    0.13
    Act Density 0.034%

    No Known Activations