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

    Neuronpedia

    INDEX
    Explanations

    specific descriptions of locations or positions

    oai_token-act-pair · gpt-3.5-turbo

    present tense forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.74
     disrupted
    -0.70
    plug
    -0.69
    successfully
    -0.68
    opted
    -0.68
    Scale
    -0.67
    Crunch
    -0.66
     rocked
    -0.66
     froze
    -0.65
    buster
    -0.65
    POSITIVE LOGITS
     Qualcomm
    0.72
     Tong
    0.72
     Teresa
    0.72
     Goldstein
    0.72
     Geneva
    0.70
     Vec
    0.69
     Greenberg
    0.68
     Dana
    0.67
     Glory
    0.66
     legions
    0.66
    Act Density 0.202%

    No Known Activations