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

    Neuronpedia

    INDEX
    Explanations

    references to specific educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hedge
    -0.16
     Hedge
    -0.16
    707
    -0.15
    รม
    -0.15
    engu
    -0.15
    .hom
    -0.15
    otte
    -0.15
    ardo
    -0.15
     comm
    -0.14
    vek
    -0.14
    POSITIVE LOGITS
    iram
    0.27
    ulen
    0.21
    iale
    0.21
    anes
    0.19
    mong
    0.19
    inkle
    0.19
    utto
    0.19
    ines
    0.18
    arget
    0.18
    ixon
    0.17
    Act Density 0.030%

    No Known Activations