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

    Neuronpedia

    INDEX
    Explanations

    references to time periods or activities that involve "after."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssp
    -0.17
    sg
    -0.16
     Aws
    -0.15
    apult
    -0.15
    ucch
    -0.15
    itionally
    -0.15
    undo
    -0.15
    swire
    -0.15
    TriState
    -0.14
    solete
    -0.14
    POSITIVE LOGITS
    thought
    0.25
    gl
    0.22
    noon
    0.20
    effects
    0.20
    math
    0.20
    mentioned
    0.19
     Glow
    0.18
    oom
    0.17
    dark
    0.17
    ViewInit
    0.17
    Act Density 0.029%

    No Known Activations