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

    Neuronpedia

    INDEX
    Explanations

    short phrases related to technological or industrial concepts

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predec
    -0.75
     scattering
    -0.68
     shroud
    -0.68
     buggy
    -0.68
     stricken
    -0.67
     shrouded
    -0.67
     multiplied
    -0.67
     scatter
    -0.67
    itably
    -0.66
     staggered
    -0.65
    POSITIVE LOGITS
    º
    1.25
    ¹
    1.16
    £
    1.12
    »
    1.03
    Į
    0.99
    ®
    0.99
    į
    0.98
    ¡
    0.98
    ¬
    0.96
    Ī
    0.96
    Act Density 0.126%

    No Known Activations