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

    Neuronpedia

    INDEX
    Explanations

    numeric measurements in the form of negative values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial or economic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kern
    -0.83
     Arabian
    -0.73
     Jelly
    -0.73
     Desert
    -0.72
     Cotton
    -0.71
     Cree
    -0.69
     Crab
    -0.69
     Sea
    -0.69
     steam
    -0.67
     Cum
    -0.67
    POSITIVE LOGITS
    related
    1.41
    based
    1.33
    driven
    1.27
    oriented
    1.24
    intensive
    1.24
    sensitive
    1.23
    seeking
    1.20
    laden
    1.18
    producing
    1.16
    saving
    1.16
    Act Density 0.113%

    No Known Activations