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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating intention or belief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intentions and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.81
    ikhail
    -0.77
    Ü
    -0.76
    ersed
    -0.67
    eers
    -0.64
     Juven
    -0.63
     Gad
    -0.62
    glers
    -0.62
    WARE
    -0.61
    swick
    -0.61
    POSITIVE LOGITS
     personally
    1.00
    poke
    0.78
     resign
    0.77
     "#
    0.72
     aback
    0.72
     quitting
    0.68
     regrets
    0.67
    uminati
    0.65
     himself
    0.64
    realDonaldTrump
    0.64
    Act Density 0.519%

    No Known Activations