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

    Neuronpedia

    INDEX
    Explanations

    patterns made up of straight vertical lines

    oai_token-act-pair · gpt-3.5-turbo

    ASCII art or special character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.87
    ngth
    -0.75
    steen
    -0.74
     ABE
    -0.69
    FY
    -0.69
    éĹĺ
    -0.68
    DragonMagazine
    -0.68
    scl
    -0.66
    ecd
    -0.66
    ãĥ£
    -0.65
    POSITIVE LOGITS
    }.
    0.66
    Kind
    0.66
    ifice
    0.63
    essee
    0.59
     turrets
    0.59
    lass
    0.59
    ese
    0.59
    ium
    0.58
    ivity
    0.58
    empt
    0.58
    Act Density 0.070%

    No Known Activations