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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ightly
    -0.19
    रत
    -0.15
    uraa
    -0.15
     Pad
    -0.15
     pow
    -0.15
     Clear
    -0.15
    ovable
    -0.14
    posix
    -0.14
    ëªħìĿĺ
    -0.14
    ýn
    -0.14
    POSITIVE LOGITS
    abin
    0.16
    agon
    0.16
     Bou
    0.15
    hana
    0.15
    aira
    0.15
    adin
    0.14
    _py
    0.14
    imb
    0.14
     bou
    0.14
     bricks
    0.14
    Act Density 0.382%

    No Known Activations