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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong positive associations or connections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chuk
    -0.81
    ãģ®éŃĶ
    -0.78
    tick
    -0.77
    arse
    -0.75
    earth
    -0.74
    hid
    -0.72
    BP
    -0.72
    ulf
    -0.71
    Strange
    -0.70
    ä¸ī
    -0.70
    POSITIVE LOGITS
     regard
    1.14
     apologies
    1.08
     regards
    1.02
     plenty
    0.89
    draw
    0.88
     exceptions
    0.87
     hindsight
    0.85
    stood
    0.85
     impunity
    0.80
     instructions
    0.80
    Act Density 0.105%

    No Known Activations