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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals or entities with significant influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥ¬
    -2.04
    ĥ½
    -1.82
    roads
    -1.75
    ments
    -1.68
    orses
    -1.66
    mente
    -1.61
    oscopy
    -1.60
    teenth
    -1.57
    ties
    -1.54
    ĨĴ
    -1.51
    POSITIVE LOGITS
    pert
    1.93
    pering
    1.70
    omo
    1.64
    isine
    1.64
    assium
    1.60
     goodness
    1.60
    per
    1.57
    yler
    1.53
    tah
    1.53
    enta
    1.52
    Act Density 0.390%

    No Known Activations