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

    Neuronpedia

    INDEX
    Explanations

    phrases related to automatic actions or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rant
    -0.17
    illos
    -0.15
    üns
    -0.15
    OKEN
    -0.15
    иÑģÑģ
    -0.15
    unker
    -0.14
    orian
    -0.14
    entine
    -0.14
    uran
    -0.14
    uch
    -0.13
    POSITIVE LOGITS
     automatically
    0.27
    aneously
    0.23
     Automatically
    0.22
     automatic
    0.22
    -automatic
    0.20
    automatic
    0.19
    /auto
    0.18
    aly
    0.17
    ullen
    0.17
    èĩªåĬ¨
    0.17
    Act Density 0.031%

    No Known Activations