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

    Neuronpedia

    INDEX
    Explanations

    references to racial or sensitive issues in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .TabStop
    -0.14
    ourg
    -0.14
    OutOf
    -0.14
    theid
    -0.14
    ClassLoader
    -0.14
    fit
    -0.14
    ucas
    -0.14
    rana
    -0.14
    esian
    -0.13
    thood
    -0.13
    POSITIVE LOGITS
     mag
    0.17
     TIME
    0.17
    mag
    0.17
     Atlantic
    0.16
     magazine
    0.16
     IDE
    0.16
    Correction
    0.16
    obia
    0.15
    Mag
    0.15
     cover
    0.15
    Act Density 0.086%

    No Known Activations