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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and questions involving consent or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orex
    -0.17
    arg
    -0.15
    ifle
    -0.15
     arg
    -0.14
    CCA
    -0.14
    zp
    -0.14
    yles
    -0.14
    zd
    -0.14
    prefs
    -0.13
    çļ®
    -0.13
    POSITIVE LOGITS
     gezocht
    0.16
     è©ķ価
    0.15
     cigaret
    0.14
     Perfect
    0.14
     Sherman
    0.14
    ÂŃi
    0.14
    /Set
    0.14
    Perfect
    0.14
    mat
    0.13
     Keywords
    0.13
    Act Density 0.209%

    No Known Activations