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

    Neuronpedia

    INDEX
    Explanations

    references to cults and cult-related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atch
    -0.17
    ctype
    -0.16
    amik
    -0.16
    lijke
    -0.16
    olen
    -0.15
    annes
    -0.15
    ening
    -0.15
    ilder
    -0.14
    avad
    -0.14
    OrCreate
    -0.14
    POSITIVE LOGITS
    urally
    0.33
    ivating
    0.31
    ivate
    0.31
    ivated
    0.29
    ivation
    0.26
    URAL
    0.25
    ured
    0.24
    IVATE
    0.23
    ivar
    0.23
    uur
    0.22
    Act Density 0.008%

    No Known Activations