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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or strong opinions

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isode
    -0.87
    ETA
    -0.77
    onding
    -0.76
    ertodd
    -0.74
    )))
    -0.72
    ))))
    -0.68
    wich
    -0.68
    imei
    -0.68
    rant
    -0.67
    ples
    -0.67
    POSITIVE LOGITS
     raining
    1.16
     impossible
    1.08
     easier
    1.05
     possible
    0.98
     difficult
    0.94
     customary
    0.92
     advisable
    0.90
     incumbent
    0.87
     conceivable
    0.85
     easy
    0.84
    Act Density 0.192%

    No Known Activations