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

    Neuronpedia

    INDEX
    Explanations

    concepts related to community and togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivor
    -0.16
    ubl
    -0.16
    erox
    -0.15
    rit
    -0.15
    pri
    -0.14
     outgoing
    -0.14
    ieux
    -0.14
     ç¥ŀ
    -0.14
    ukt
    -0.14
    UPLE
    -0.14
    POSITIVE LOGITS
     into
    0.30
    ToFront
    0.27
     onto
    0.27
     alive
    0.26
     forth
    0.26
     together
    0.26
     Into
    0.24
     closer
    0.23
    into
    0.23
    Into
    0.23
    Act Density 0.060%

    No Known Activations