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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intl
    -0.16
    £
    -0.14
     Fant
    -0.14
    battle
    -0.14
    éré
    -0.14
    충
    -0.14
     Patton
    -0.13
    наÑĢÑĥж
    -0.13
     Klaus
    -0.13
    lems
    -0.13
    POSITIVE LOGITS
    ifter
    0.15
    650
    0.15
     Fowler
    0.15
    окон
    0.14
    گر
    0.14
    ROUGH
    0.14
     Bis
    0.14
     Cruiser
    0.14
    icial
    0.13
    eldorf
    0.13
    Act Density 0.003%

    No Known Activations