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

    Neuronpedia

    INDEX
    Explanations

    words that describe high standards or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ne
    -0.16
    ccoli
    -0.16
    923
    -0.15
    istrovstvÃŃ
    -0.14
    274
    -0.14
    plen
    -0.14
    .mods
    -0.14
    ุà¹ī
    -0.14
    vine
    -0.14
    ccess
    -0.14
    POSITIVE LOGITS
    borg
    0.17
    .Sound
    0.15
    hots
    0.15
    RuleContext
    0.14
     Retro
    0.14
     Conservative
    0.14
    apore
    0.13
    olet
    0.13
    dum
    0.13
    .rule
    0.13
    Act Density 0.000%

    No Known Activations