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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or doubt about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.84
    itton
    -0.75
    ismo
    -0.69
    pez
    -0.68
    instead
    -0.66
    yes
    -0.63
    utz
    -0.61
    unknown
    -0.61
     instead
    -0.60
    rowing
    -0.59
    POSITIVE LOGITS
     anymore
    1.22
     bothered
    1.04
     remotely
    1.00
     anywhere
    0.99
     whatsoever
    0.92
     nor
    0.90
     bother
    0.89
     necessarily
    0.88
     anything
    0.87
     bothering
    0.83
    Act Density 0.098%

    No Known Activations