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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and specific numeric references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.86
    ãĤ©
    -0.80
    IUM
    -0.80
    earable
    -0.76
    ulkan
    -0.74
    Deal
    -0.72
    ensable
    -0.71
    EEE
    -0.70
    ADA
    -0.69
    ONSORED
    -0.69
    POSITIVE LOGITS
     Ange
    0.73
     fateful
    0.71
    teenth
    0.71
     final
    0.68
     thirds
    0.68
     onward
    0.66
     eighth
    0.65
     sevent
    0.63
     fourth
    0.62
    rew
    0.61
    Act Density 0.030%

    No Known Activations