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

    Neuronpedia

    INDEX
    Explanations

    code structures involving loops and parent-child relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bullet
    -0.16
    ÃĹ↵↵
    -0.15
    ULE
    -0.14
    stamp
    -0.14
    anca
    -0.14
    badge
    -0.14
    bullet
    -0.14
    yth
    -0.13
    evice
    -0.13
     Claudia
    -0.13
    POSITIVE LOGITS
    osit
    0.16
    AccessType
    0.15
    837
    0.15
     Tatto
    0.14
    olian
    0.14
    VML
    0.14
    poll
    0.14
    алом
    0.14
    ayaran
    0.14
    onz
    0.13
    Act Density 0.068%

    No Known Activations