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

    Neuronpedia

    INDEX
    Explanations

    references to destination points or elements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asan
    -0.17
    enticate
    -0.16
    oline
    -0.16
    ording
    -0.15
    uff
    -0.15
    elic
    -0.14
    thers
    -0.14
    _vi
    -0.14
    ellen
    -0.14
    ervo
    -0.14
    POSITIVE LOGITS
    ãĥ«ãĥī
    0.18
    637
    0.14
    ylvania
    0.14
    ortion
    0.14
    iny
    0.14
     McM
    0.14
    AGMA
    0.14
    iveau
    0.14
     Tess
    0.13
    -toggler
    0.13
    Act Density 0.011%

    No Known Activations