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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating organization or preparation of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ«
    -0.17
     ant
    -0.15
     ram
    -0.15
    گز
    -0.15
    wend
    -0.14
    ota
    -0.14
    vez
    -0.14
    ener
    -0.14
    een
    -0.14
    iggers
    -0.14
    POSITIVE LOGITS
    abi
    0.17
    acific
    0.16
    .yy
    0.16
    ãĥ³ãĤ¬
    0.15
    ABI
    0.14
    ainers
    0.14
    οι
    0.14
    aminer
    0.14
    omo
    0.14
    elry
    0.14
    Act Density 0.026%

    No Known Activations