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

    Neuronpedia

    INDEX
    Explanations

    instances of directives or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verts
    -0.16
    urai
    -0.16
    ucker
    -0.16
    allest
    -0.16
    ahi
    -0.15
    uka
    -0.15
     ÙĪاج
    -0.14
    lico
    -0.14
    lÃŃ
    -0.14
     bleeding
    -0.14
    POSITIVE LOGITS
    ovsky
    0.15
    odus
    0.14
    aris
    0.14
     Gad
    0.14
    omens
    0.14
    äge
    0.13
    tee
    0.13
    spacer
    0.13
    (coder
    0.13
    letter
    0.13
    Act Density 0.001%

    No Known Activations