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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "for" that indicate the purpose or intention behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esion
    -0.16
    bis
    -0.15
    asper
    -0.14
     Obr
    -0.13
    tram
    -0.13
    undy
    -0.13
    .Unity
    -0.13
    abyrinth
    -0.13
    urance
    -0.13
    Ñĩно
    -0.13
    POSITIVE LOGITS
     addCriterion
    0.18
    ÙĦØŃ
    0.16
     overlap
    0.16
    Äįin
    0.15
    oux
    0.14
     greater
    0.14
    ī
    0.14
     dise
    0.14
    ateur
    0.14
     Dise
    0.14
    Act Density 0.058%

    No Known Activations