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

    Neuronpedia

    INDEX
    Explanations

    terms related to purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.18
    å¯
    -0.17
    ån
    -0.16
    rec
    -0.16
    rael
    -0.16
    ishly
    -0.16
    sel
    -0.15
    orna
    -0.15
    eding
    -0.15
    agy
    -0.15
    POSITIVE LOGITS
    ful
    0.41
    fully
    0.40
    fulness
    0.33
    FUL
    0.31
    -built
    0.28
    FULL
    0.23
    full
    0.23
    st
    0.19
    lessly
    0.18
    uilt
    0.18
    Act Density 0.022%

    No Known Activations