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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "conflict" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ile
    -0.21
    auer
    -0.16
    вол
    -0.16
    errupted
    -0.15
    iles
    -0.15
     Banc
    -0.15
    igkeit
    -0.15
    erk
    -0.15
    IU
    -0.15
    er
    -0.14
    POSITIVE LOGITS
     conf
    0.39
    etti
    0.28
     Conf
    0.27
    /conf
    0.26
    idential
    0.25
    (conf
    0.25
    Conf
    0.24
     Confeder
    0.23
    essions
    0.23
    ident
    0.23
    Act Density 0.006%

    No Known Activations