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

    Neuronpedia

    INDEX
    Explanations

    phrases related to philosophical concepts and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢº
    -0.76
     ($
    -0.76
    -$
    -0.73
     TMZ
    -0.72
    gc
    -0.71
    Bloomberg
    -0.71
    tackle
    -0.70
    ESPN
    -0.68
     Stacy
    -0.68
    oops
    -0.68
    POSITIVE LOGITS
     latter
    1.30
     slightest
    1.12
     earliest
    0.98
     same
    0.95
     greatest
    0.95
     remainder
    0.94
     aforementioned
    0.93
     smallest
    0.92
     simplest
    0.92
     entirety
    0.91
    Act Density 1.226%

    No Known Activations