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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "outside" or external environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardi
    -0.17
    holes
    -0.16
    esters
    -0.15
     Roths
    -0.15
    ollider
    -0.14
    RESULTS
    -0.14
    мÑı
    -0.14
    Ñĸли
    -0.14
    .clf
    -0.14
    rypton
    -0.14
    POSITIVE LOGITS
     of
    0.26
    /out
    0.23
    outside
    0.21
     outside
    0.21
    Outside
    0.20
     Outside
    0.20
     bounds
    0.19
    jÅ¡ÃŃ
    0.18
    /in
    0.18
    -of
    0.17
    Act Density 0.017%

    No Known Activations