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

    Neuronpedia

    INDEX
    Explanations

    comparative or evaluative expressions related to capability or adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Derbyniad
    -0.61
    Datuak
    -0.56
    GEBURTSDATUM
    -0.56
    Rohy
    -0.55
    AnimationsModule
    -0.54
    RectangleBorder
    -0.54
    twimg
    -0.54
    Notae
    -0.53
    PreInfinity
    -0.53
     jLabel
    -0.52
    POSITIVE LOGITS
     possibly
    1.23
     Possibly
    1.09
    possibly
    1.05
    Possibly
    1.02
     possible
    0.98
     Possible
    0.92
    Possible
    0.88
    possible
    0.85
     POSSIBLE
    0.82
     possi
    0.81
    Act Density 0.189%

    No Known Activations