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

    Neuronpedia

    INDEX
    Explanations

    references to relationships among concepts or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saltar
    -0.76
    bcryptjs
    -0.69
    Bronnen
    -0.68
    Tikang
    -0.66
     utafitiHapana
    -0.64
     Jefus
    -0.63
    Портал
    -0.62
    expandindo
    -0.62
     Chrift
    -0.62
     ་་
    -0.62
    POSITIVE LOGITS
    InjectAttribute
    0.57
     a
    0.55
    ↵↵
    0.53
     its
    0.48
    UAGES
    0.48
     Tapatalk
    0.47
    ↵↵↵
    0.47
     décider
    0.47
    ,
    0.46
    .
    0.45
    Act Density 0.917%

    No Known Activations