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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or subjective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [B
    -0.14
    cape
    -0.14
    rios
    -0.14
    åĵ
    -0.13
    yles
    -0.13
    ró
    -0.13
    Ñħи
    -0.13
    _CONST
    -0.13
    sha
    -0.13
    æı
    -0.13
    POSITIVE LOGITS
     other
    0.17
    _SCR
    0.15
     whether
    0.15
     others
    0.14
    enser
    0.14
    coni
    0.14
     nữa
    0.14
     samot
    0.14
    intl
    0.14
     دÛĮگر
    0.14
    Act Density 0.017%

    No Known Activations