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

    Neuronpedia

    INDEX
    Explanations

    elements related to adjectives and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eros
    -0.20
    pany
    -0.15
    ória
    -0.14
    gers
    -0.14
    odus
    -0.14
    slaught
    -0.14
    erus
    -0.13
    790
    -0.13
    VIC
    -0.13
    iros
    -0.13
    POSITIVE LOGITS
     Dough
    0.15
     Defaults
    0.15
     âĨĴ↵↵
    0.15
    Opaque
    0.14
     Vest
    0.14
    artz
    0.14
     вин
    0.14
    kaar
    0.14
    fall
    0.14
    aman
    0.14
    Act Density 0.040%

    No Known Activations