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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KK
    -0.69
     Kut
    -0.68
     Receiver
    -0.65
    Integ
    -0.65
     Shuttle
    -0.65
     Chero
    -0.64
    rez
    -0.64
    ucks
    -0.64
    BB
    -0.62
    Rules
    -0.61
    POSITIVE LOGITS
     sorcery
    0.87
    quila
    0.81
    opia
    0.73
    conom
    0.70
     mankind
    0.70
    etheless
    0.70
     mortals
    0.68
    shine
    0.66
    ergy
    0.65
    nesota
    0.64
    Act Density 0.124%

    No Known Activations