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

    Neuronpedia

    INDEX
    Explanations

    phrases and prepositions that indicate relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jos
    -0.17
    amas
    -0.15
     GURL
    -0.15
     nackte
    -0.14
    otime
    -0.14
     Král
    -0.14
    ANNEL
    -0.13
    íĥ
    -0.13
    FRING
    -0.13
    usercontent
    -0.13
    POSITIVE LOGITS
     various
    0.30
     both
    0.25
     several
    0.21
     Various
    0.20
    åIJĦç§į
    0.20
    both
    0.18
     different
    0.18
     både
    0.18
    Various
    0.18
     actual
    0.17
    Act Density 0.042%

    No Known Activations