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

    Neuronpedia

    INDEX
    Explanations

    phrases that specify a particular subject of interest or importance

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boarding
    -0.58
     Sad
    -0.58
     Pass
    -0.57
     Eye
    -0.56
     Mit
    -0.56
     Emergency
    -0.55
     Haz
    -0.54
     Nek
    -0.54
     Caucus
    -0.54
     Corps
    -0.54
    POSITIVE LOGITS
     accompanies
    0.85
     includes
    0.83
     corresponds
    0.83
     exceeds
    0.83
     fateful
    0.82
     surrounds
    0.82
     resulted
    0.79
     satisfies
    0.79
    eatures
    0.79
     occurs
    0.79
    Act Density 0.330%

    No Known Activations