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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     friend
    -0.08
    RIEND
    -0.08
    ãģĭãģij
    -0.07
     sibling
    -0.07
     Friend
    -0.07
    ichen
    -0.06
    ÑĮко
    -0.06
     rival
    -0.06
     Pai
    -0.06
     FRIEND
    -0.06
    POSITIVE LOGITS
    ayer
    0.06
    nameof
    0.06
    ħĮ
    0.06
    erken
    0.06
    odon
    0.06
    \\.
    0.06
    actus
    0.06
    ilog
    0.06
    ège
    0.06
    obox
    0.06
    Act Density 0.061%

    No Known Activations