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

    Neuronpedia

    INDEX
    Explanations

    lines of code or configuration entries that include specific format indicators or syntax structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antu
    -0.16
    ilo
    -0.15
    ala
    -0.15
    ubs
    -0.15
    raph
    -0.14
    scribe
    -0.14
    ped
    -0.14
    antium
    -0.14
    eto
    -0.14
    ythe
    -0.14
    POSITIVE LOGITS
    uisse
    0.16
    ussen
    0.16
    ãĥĹãĥ©
    0.14
    ãĥ«
    0.13
    cloak
    0.13
    icycle
    0.13
    IRO
    0.13
    tid
    0.13
    ifty
    0.13
    igest
    0.13
    Act Density 0.016%

    No Known Activations