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

    Neuronpedia

    INDEX
    Explanations

    references to astrology or astrological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leans
    -0.19
    entanyl
    -0.18
    erse
    -0.17
    ráf
    -0.16
    radient
    -0.16
    rant
    -0.16
    otor
    -0.16
    lems
    -0.16
    rpc
    -0.16
    .metro
    -0.16
    POSITIVE LOGITS
    ounding
    0.25
    ute
    0.24
    ound
    0.24
    roph
    0.23
    ounded
    0.23
    .literal
    0.22
    igmat
    0.22
    utely
    0.21
    hma
    0.21
    UTE
    0.20
    Act Density 0.007%

    No Known Activations