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

    Neuronpedia

    INDEX
    Explanations

    terms and references related to witchcraft and witches

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

    witch, witches, witchcraft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onResume
    -0.61
     Largo
    -0.59
     Bono
    -0.58
     Dura
    -0.54
     Tada
    -0.52
    anyeol
    -0.51
     Redondo
    -0.51
    久
    -0.50
    sohn
    -0.49
    ypep
    -0.49
    POSITIVE LOGITS
     Witch
    1.26
     witch
    1.20
    Witch
    1.14
     witches
    1.10
     witchcraft
    0.98
    witch
    0.93
     Witches
    0.91
     bruja
    0.82
    🧙
    0.71
     createState
    0.70
    Act Density 0.008%

    No Known Activations