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

    Neuronpedia

    INDEX
    Explanations

    references to purpose or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igans
    -0.20
    ån
    -0.19
    sid
    -0.18
    redo
    -0.17
    eyn
    -0.17
    imits
    -0.17
    rec
    -0.16
    endar
    -0.16
    roller
    -0.16
    orna
    -0.15
    POSITIVE LOGITS
    ful
    0.51
    fully
    0.44
    fulness
    0.40
    FUL
    0.36
    -built
    0.32
    full
    0.30
    st
    0.25
    FULL
    0.25
     statement
    0.24
     behind
    0.23
    Act Density 0.023%

    No Known Activations