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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "a" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.79
    Anim
    -0.71
     instead
    -0.71
    olicy
    -0.70
    Discussion
    -0.70
    Effects
    -0.69
    Thom
    -0.69
    scenes
    -0.68
    Ont
    -0.68
    scl
    -0.68
    POSITIVE LOGITS
     dime
    1.03
     slightest
    1.03
     bunch
    0.95
     anymore
    0.92
     lot
    0.90
     definitive
    0.90
     hint
    0.88
     clue
    0.86
     fuss
    0.85
     coincidence
    0.84
    Act Density 0.183%

    No Known Activations