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

    Neuronpedia

    INDEX
    Explanations

    the start of a sentence, typically indicating the beginning of a statement or idea

    oai_token-act-pair · gpt-3.5-turbo

    significant introductory phrases and reference points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rall
    -0.68
     Redmond
    -0.67
    zig
    -0.63
    aign
    -0.63
     Vaugh
    -0.63
     Lyon
    -0.62
     CPC
    -0.60
     BYU
    -0.60
     Pompe
    -0.60
     Reed
    -0.60
    POSITIVE LOGITS
    itialized
    0.88
    cano
    0.74
    hiro
    0.69
    bsp
    0.69
    orem
    0.68
     Started
    0.65
    SourceFile
    0.65
    notation
    0.65
    ths
    0.63
    pected
    0.62
    Act Density 0.267%

    No Known Activations