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

    Neuronpedia

    INDEX
    Explanations

    references to counterparts or equivalents in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.17
    burgh
    -0.16
    ULAR
    -0.15
    tic
    -0.14
    ĤŃ
    -0.14
    croft
    -0.14
    BY
    -0.14
    zin
    -0.14
    WithOptions
    -0.14
    omet
    -0.13
    POSITIVE LOGITS
    ies
    0.15
    jes
    0.14
    709
    0.14
    rons
    0.14
    ages
    0.13
    916
    0.13
    (s
    0.13
     Chan
    0.13
    sth
    0.13
    xbd
    0.13
    Act Density 0.005%

    No Known Activations