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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their relationships within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dark killing skillsets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actionPerformed
    -0.50
     AssertionError
    -0.49
     UserController
    -0.48
     paroisse
    -0.48
    aibo
    -0.47
    蒻
    -0.46
    Хьажоргаш
    -0.46
     SHOCK
    -0.45
    UIControlState
    -0.45
     OFDb
    -0.45
    POSITIVE LOGITS
     Hannibal
    0.60
     Verhaltens
    0.45
     Silence
    0.43
    nibal
    0.42
     behaviour
    0.41
     Reichs
    0.41
     behavioural
    0.41
     Lec
    0.40
     eating
    0.39
    Silence
    0.39
    Act Density 0.037%

    No Known Activations