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

    Neuronpedia

    INDEX
    Explanations

    uppercase letters and their combinations in variable names, methods, or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovky
    -0.16
    WithOptions
    -0.16
    umbn
    -0.16
     mailbox
    -0.15
     puck
    -0.15
    seau
    -0.15
    ovah
    -0.15
    hab
    -0.15
    endale
    -0.15
    haf
    -0.15
    POSITIVE LOGITS
    ritable
    0.21
    iz
    0.18
    affle
    0.18
    ont
    0.18
    wise
    0.17
    WISE
    0.17
    rox
    0.17
    ysi
    0.16
    acom
    0.16
    ai
    0.16
    Act Density 0.020%

    No Known Activations