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

    Neuronpedia

    INDEX
    Explanations

    terms related to booking and cancellation policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.17
    paren
    -0.16
    undy
    -0.15
    340
    -0.15
    ude
    -0.14
    lion
    -0.14
    eree
    -0.14
    Paren
    -0.14
    esen
    -0.14
    chio
    -0.13
    POSITIVE LOGITS
     Bench
    0.17
    emiz
    0.17
    okens
    0.16
    eya
    0.15
    èĬ
    0.15
    .tc
    0.14
     bench
    0.14
    utr
    0.14
    ields
    0.13
    illac
    0.13
    Act Density 0.025%

    No Known Activations