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

    Neuronpedia

    INDEX
    Explanations

    descriptions or statements made about a topic

    oai_token-act-pair · gpt-3.5-turbo

    statements and reports regarding allegations and official communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acqu
    -0.66
    Plex
    -0.65
    obyl
    -0.62
    pel
    -0.62
     stump
    -0.62
    ardless
    -0.61
    axe
    -0.60
    uncture
    -0.60
     Flavoring
    -0.60
     Maker
    -0.59
    POSITIVE LOGITS
     quoting
    0.79
     adding
    0.73
    thens
    0.68
     omin
    0.67
    iffs
    0.65
     cris
    0.65
     bluntly
    0.64
     titled
    0.61
     convinc
    0.59
     added
    0.59
    Act Density 0.176%

    No Known Activations