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

    Neuronpedia

    INDEX
    Explanations

    conditional statements regarding desires or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĹ↵↵
    -0.16
    zk
    -0.15
    EMON
    -0.15
     @{↵
    -0.15
     pros
    -0.14
    arc
    -0.14
     grounds
    -0.14
    æ¼ı
    -0.14
    scenario
    -0.14
    aley
    -0.14
    POSITIVE LOGITS
     LENG
    0.16
    tica
    0.16
    .flink
    0.15
    asher
    0.15
    dü
    0.15
    abeth
    0.15
    sian
    0.14
    undan
    0.14
    cheng
    0.14
    banks
    0.14
    Act Density 0.215%

    No Known Activations