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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation, possibility, and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #+#
    -0.78
    PerformLayout
    -0.64
    abestanden
    -0.63
     فريبيس
    -0.61
    ⤹
    -0.57
    featureID
    -0.56
     ويكيميديا
    -0.55
    ropshire
    -0.54
    Pey
    -0.54
    AnimationsModule
    -0.54
    POSITIVE LOGITS
     not
    0.77
     indeed
    0.73
     also
    0.71
     certainly
    0.68
     ciertamente
    0.58
     often
    0.58
     always
    0.56
     be
    0.56
     surely
    0.55
     nemlig
    0.53
    Act Density 0.532%

    No Known Activations