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

    Neuronpedia

    INDEX
    Explanations

    references to specific parts or components of a machine or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.16
    l
    -0.15
     theory
    -0.15
    092
    -0.15
    ↵
    -0.14
    988
    -0.14
    eno
    -0.14
    ummies
    -0.14
     instead
    -0.14
    ahr
    -0.14
    POSITIVE LOGITS
     Schwarz
    0.19
    swick
    0.19
    uzey
    0.18
    teil
    0.16
    arez
    0.16
    ableObject
    0.15
    assis
    0.15
    wang
    0.15
    ForObject
    0.15
    /Dk
    0.15
    Act Density 0.274%

    No Known Activations