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

    Neuronpedia

    INDEX
    Explanations

    action-oriented verbs related to speaking and performing in public contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omu
    -0.07
    ÑĢанениÑı
    -0.07
    çĿĽ
    -0.06
    arcy
    -0.06
    reeze
    -0.06
     Asked
    -0.06
    tober
    -0.06
     Excell
    -0.06
    abble
    -0.06
    opol
    -0.06
    POSITIVE LOGITS
    lfw
    0.08
     Dün
    0.07
    OUCH
    0.07
     Marino
    0.06
     kit
    0.06
    084
    0.06
     Paladin
    0.06
     Mädchen
    0.06
    crap
    0.06
    dete
    0.06
    Act Density 0.009%

    No Known Activations