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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating achievement or accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mtree
    -0.17
    ubl
    -0.17
    ASI
    -0.15
     Gone
    -0.15
    icina
    -0.14
     пон
    -0.14
    ampp
    -0.14
    dana
    -0.14
    itored
    -0.14
     cref
    -0.14
    POSITIVE LOGITS
     somehow
    0.20
     somew
    0.18
    -ÑĤаки
    0.17
     manages
    0.16
     get
    0.16
     enough
    0.15
    768
    0.15
     Ded
    0.15
     managed
    0.15
    gu
    0.14
    Act Density 0.044%

    No Known Activations