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

    Neuronpedia

    INDEX
    Explanations

    terms related to witches and witchcraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shima
    -0.17
    ležit
    -0.15
    *sp
    -0.15
    otas
    -0.15
    iece
    -0.15
    undy
    -0.15
    rrha
    -0.15
    ailles
    -0.14
    edList
    -0.14
    ÑĪев
    -0.14
    POSITIVE LOGITS
    craft
    0.24
    ery
    0.21
    y
    0.19
    osh
    0.18
    etur
    0.17
    ell
    0.16
    abee
    0.16
    ibe
    0.16
    like
    0.15
     Witch
    0.15
    Act Density 0.010%

    No Known Activations