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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey quantities or fullness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugar
    -0.17
    ucht
    -0.17
    ë§Ŀ
    -0.16
    aha
    -0.15
    adh
    -0.15
    eways
    -0.14
    ely
    -0.14
     construct
    -0.14
     Vide
    -0.14
    iry
    -0.14
    POSITIVE LOGITS
    ermal
    0.16
    unj
    0.15
    SGlobal
    0.15
     Tale
    0.15
    ful
    0.15
    º
    0.15
    osite
    0.14
    Ñħод
    0.14
    sed
    0.14
    jax
    0.14
    Act Density 0.081%

    No Known Activations