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

    Neuronpedia

    INDEX
    Explanations

    references to warnings and predictions about future events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umblr
    -0.15
    upal
    -0.15
    arov
    -0.15
    abeth
    -0.14
    ORA
    -0.14
    iros
    -0.14
    SEO
    -0.14
    osu
    -0.14
    eczy
    -0.13
    alat
    -0.13
    POSITIVE LOGITS
    anka
    0.19
     predictions
    0.17
     Crud
    0.17
     prediction
    0.17
     Hubb
    0.15
    assis
    0.15
    ients
    0.15
    è¦
    0.15
    jud
    0.14
    覧
    0.14
    Act Density 0.290%

    No Known Activations