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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allon
    -0.16
    gia
    -0.15
    lluminate
    -0.15
    _ASSUME
    -0.15
    uibModal
    -0.15
    afka
    -0.14
    å®Ĺ
    -0.14
    uze
    -0.14
    ucket
    -0.14
    ÙĬÙĩ
    -0.14
    POSITIVE LOGITS
     instead
    0.21
    instead
    0.20
    Instead
    0.19
     Instead
    0.19
     Witt
    0.16
     fest
    0.14
    angu
    0.14
    ен
    0.14
    fully
    0.14
    зÑĥ
    0.14
    Act Density 0.036%

    No Known Activations