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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and organized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coming
    -0.16
    owitz
    -0.16
     ид
    -0.15
     outgoing
    -0.15
    croft
    -0.15
     taking
    -0.15
    تاب
    -0.15
     Insider
    -0.14
    ivor
    -0.14
     going
    -0.14
    POSITIVE LOGITS
    ToFront
    0.23
     together
    0.22
     into
    0.22
     forth
    0.22
     closer
    0.21
     Into
    0.20
     alive
    0.19
     Clo
    0.19
    Into
    0.19
     back
    0.18
    Act Density 0.039%

    No Known Activations