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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "few" suggesting a focus on quantity or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.16
    gio
    -0.14
    ati
    -0.14
     Plenty
    -0.14
    /OR
    -0.14
     ong
    -0.14
     Forgot
    -0.14
    ORIES
    -0.13
    791
    -0.13
    cid
    -0.13
    POSITIVE LOGITS
     dozen
    0.37
     hundred
    0.27
     thousand
    0.24
    /all
    0.19
     Hundred
    0.18
     málo
    0.18
     different
    0.18
     extra
    0.17
     деÑģÑıÑĤ
    0.17
    est
    0.17
    Act Density 0.059%

    No Known Activations