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

    Neuronpedia

    INDEX
    Explanations

    discussions about knowledge, experience, and collaboration among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥĥãĤ¯
    -0.17
    aven
    -0.15
    iker
    -0.14
     chamber
    -0.14
     off
    -0.14
     proportional
    -0.14
    emoc
    -0.14
     Hit
    -0.14
    atcher
    -0.14
     agree
    -0.14
    POSITIVE LOGITS
     superior
    0.23
     Superior
    0.19
     ahead
    0.19
     whereas
    0.19
     envy
    0.18
     superiority
    0.17
     Ahead
    0.17
    ahead
    0.16
     Whereas
    0.16
    -ahead
    0.15
    Act Density 0.208%

    No Known Activations