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

    Neuronpedia

    INDEX
    Explanations

    references to names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eq
    -0.21
    es
    -0.19
    ess
    -0.18
    esan
    -0.18
    iom
    -0.17
    ezi
    -0.17
    ett
    -0.17
    egl
    -0.17
    ez
    -0.16
    elly
    -0.16
    POSITIVE LOGITS
    los
    0.22
    lop
    0.21
    loi
    0.19
    lok
    0.18
    tings
    0.18
    ld
    0.18
    loe
    0.17
    bert
    0.17
    ldata
    0.17
    ting
    0.17
    Act Density 0.031%

    No Known Activations