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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.78
    isin
    -0.74
    ãĥį
    -0.71
    Layer
    -0.69
    =#
    -0.68
    Line
    -0.67
     instead
    -0.65
     periodically
    -0.64
     @@
    -0.63
    Rex
    -0.63
    POSITIVE LOGITS
     slightest
    1.83
     usual
    1.22
     same
    1.10
     nor
    0.99
     entirety
    0.98
     exact
    0.95
     smallest
    0.94
     specifics
    0.91
     hardest
    0.89
     anymore
    0.89
    Act Density 0.340%

    No Known Activations