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

    Neuronpedia

    INDEX
    Explanations

    terms related to health, safety, and wellness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imens
    -0.17
    ennen
    -0.17
    ephir
    -0.16
    tim
    -0.15
    inel
    -0.15
    uzzi
    -0.15
    emoth
    -0.14
     ấn
    -0.14
    arness
    -0.14
     til
    -0.14
    POSITIVE LOGITS
    pson
    0.16
     $_[
    0.15
    êu
    0.15
    HQ
    0.14
    айд
    0.14
     Wilderness
    0.14
    atr
    0.14
    ranges
    0.14
     Ire
    0.13
     Diss
    0.13
    Act Density 1.947%

    No Known Activations