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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional struggles and interpersonal conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.16
    eddar
    -0.15
    afort
    -0.15
    hal
    -0.14
    ointed
    -0.14
    hari
    -0.14
    landa
    -0.14
    umar
    -0.14
    Ø´ÙĬ
    -0.14
    udur
    -0.14
    POSITIVE LOGITS
     Rogue
    0.15
    Interop
    0.15
    gan
    0.15
    æ··
    0.15
    amet
    0.14
    ogue
    0.14
     Garrison
    0.14
    ERGE
    0.14
    è¡Ľ
    0.14
    NECT
    0.14
    Act Density 0.302%

    No Known Activations