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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toronto
    -0.49
     Pa
    -0.48
    穣
    -0.47
    Itoa
    -0.45
     useCallback
    -0.45
     BoxFit
    -0.44
    vábbi
    -0.43
     ad
    -0.43
    preprocessing
    -0.43
    ("'"
    -0.43
    POSITIVE LOGITS
     houſe
    0.84
     whoſe
    0.82
     fevere
    0.82
     myſelf
    0.81
     ſtate
    0.81
     itſelf
    0.78
     purpoſe
    0.78
     Efq
    0.78
     Roskov
    0.78
     Theſe
    0.77
    Act Density 0.155%

    No Known Activations