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

    Neuronpedia

    INDEX
    Explanations

    intense expressions of denial or refusal related to allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synonym
    -0.17
    Ùħز
    -0.17
    baum
    -0.15
    esz
    -0.14
    edy
    -0.14
    olk
    -0.14
     Zeit
    -0.14
    ÑģÑĭ
    -0.13
     Favorite
    -0.13
    _PAD
    -0.13
    POSITIVE LOGITS
    ogle
    0.16
    anda
    0.15
    ĵn
    0.15
    ifold
    0.14
    aper
    0.14
    emic
    0.14
     Barr
    0.14
    禮
    0.13
     fat
    0.13
     charges
    0.13
    Act Density 0.169%

    No Known Activations