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

    Neuronpedia

    INDEX
    Explanations

    elements related to aggression and unique creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iegel
    -0.15
    åĬĽéĩı
    -0.15
    bsolute
    -0.15
    vala
    -0.14
    ouver
    -0.14
    adiens
    -0.14
    orraine
    -0.14
    gart
    -0.14
    ungeons
    -0.14
    ecome
    -0.14
    POSITIVE LOGITS
    odont
    0.15
    wort
    0.15
     embr
    0.14
    prenom
    0.14
     Philipp
    0.14
    ynchronously
    0.14
    (predicate
    0.14
     foss
    0.14
    .Atomic
    0.13
     TForm
    0.13
    Act Density 0.029%

    No Known Activations