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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lack or absence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of minimal or no quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tera
    -0.74
    aram
    -0.67
    gypt
    -0.66
    itect
    -0.64
     Chero
    -0.57
    Stage
    -0.55
    Exec
    -0.54
    YC
    -0.54
     Columb
    -0.52
    rive
    -0.52
    POSITIVE LOGITS
     no
    0.90
    nothing
    0.88
     nothing
    0.88
     none
    0.85
    no
    0.84
     NO
    0.81
    existent
    0.78
     nonexistent
    0.75
     nil
    0.73
     nowhere
    0.73
    Act Density 0.053%

    No Known Activations