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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oux
    -0.16
    quina
    -0.15
    andum
    -0.15
    wers
    -0.15
    illy
    -0.15
    ournal
    -0.15
    aille
    -0.14
    agma
    -0.14
     plant
    -0.14
    wer
    -0.14
    POSITIVE LOGITS
     than
    0.18
     besides
    0.18
     apart
    0.17
     кÑĢоме
    0.17
    umin
    0.17
    _than
    0.17
     except
    0.16
     Agenda
    0.16
    _ASSUME
    0.15
    than
    0.15
    Act Density 0.065%

    No Known Activations