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

    Neuronpedia

    INDEX
    Explanations

    expressions of distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    empo
    -0.17
    richt
    -0.15
    chter
    -0.15
    adors
    -0.15
    baum
    -0.15
    making
    -0.14
    dings
    -0.14
     Moran
    -0.14
    hammer
    -0.14
    emas
    -0.14
    POSITIVE LOGITS
    -reaching
    0.23
     à¹Ĩ
    0.17
    reach
    0.16
    ARRANT
    0.15
     enough
    0.15
    er
    0.15
    thest
    0.15
    ToMany
    0.15
    mland
    0.14
     Enough
    0.14
    Act Density 0.064%

    No Known Activations