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

    Neuronpedia

    INDEX
    Explanations

    phrases that express confusion or disapproval about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erset
    -0.17
    alie
    -0.17
    ucker
    -0.16
     CGRectGet
    -0.16
    positor
    -0.15
    chwitz
    -0.15
    linger
    -0.15
     hete
    -0.14
    imeters
    -0.14
    rosse
    -0.14
    POSITIVE LOGITS
     tir
    0.16
     Zig
    0.16
    Vectorizer
    0.15
     Bender
    0.15
    iq
    0.15
     sting
    0.15
    éĢ¸
    0.15
    ामà¤Ĺ
    0.14
    stick
    0.14
    kah
    0.14
    Act Density 0.170%

    No Known Activations