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

    Neuronpedia

    INDEX
    Explanations

    dynamic actions or processes being performed by living beings

    oai_token-act-pair · gpt-3.5-turbo

    action verbs associated with various activities and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.64
     Ange
    -0.62
     Longh
    -0.59
     Rug
    -0.57
    uana
    -0.56
     Almighty
    -0.56
    é¾įå
    -0.54
    Cub
    -0.54
    ourke
    -0.54
     Brow
    -0.53
    POSITIVE LOGITS
     themselves
    1.18
    ingly
    0.99
    eth
    0.95
     their
    0.95
    ings
    0.88
    their
    0.82
    selves
    0.81
    fully
    0.81
     differently
    0.79
     THEIR
    0.78
    Act Density 0.455%

    No Known Activations