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

    Neuronpedia

    INDEX
    Explanations

    terms related to ambiguity or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xor
    -0.19
    eza
    -0.17
    ez
    -0.17
    icamente
    -0.17
    eva
    -0.16
    ean
    -0.16
    icz
    -0.16
    ega
    -0.16
    ea
    -0.15
    ek
    -0.15
    POSITIVE LOGITS
    ist
    0.22
    eterminate
    0.21
    ented
    0.21
    isc
    0.21
    istinguish
    0.21
    ator
    0.20
    isp
    0.20
    ub
    0.19
    iss
    0.19
    ignant
    0.18
    Act Density 0.006%

    No Known Activations