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

    Neuronpedia

    INDEX
    Explanations

    instances of inquiry and questioning in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippo
    -0.17
    olah
    -0.16
    _TA
    -0.15
    iesel
    -0.15
    redient
    -0.15
    decess
    -0.14
    amak
    -0.14
    åħ¥ãĤĮ
    -0.14
    erer
    -0.14
    akat
    -0.13
    POSITIVE LOGITS
    ayne
    0.16
    KIT
    0.15
     Hem
    0.14
    ende
    0.14
    let
    0.14
    ody
    0.14
    Kit
    0.14
     Esper
    0.13
     æĶ¯
    0.13
     Europ
    0.13
    Act Density 0.028%

    No Known Activations