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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating learning preferences and educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esser
    -0.19
    braco
    -0.18
    .GraphicsUnit
    -0.18
    uros
    -0.17
    imary
    -0.17
    LEAR
    -0.17
    viar
    -0.15
    antro
    -0.15
    gressor
    -0.15
    peq
    -0.15
    POSITIVE LOGITS
    stat
    0.19
    ↵
    0.16
    Stat
    0.16
     etc
    0.15
     whereas
    0.15
    /stat
    0.15
     bert
    0.14
     Carey
    0.14
    933
    0.14
    jay
    0.14
    Act Density 0.079%

    No Known Activations