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

    Neuronpedia

    INDEX
    Explanations

    certainty or assurance in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -1.03
     Obrador
    -0.85
     iconFacebook
    -0.85
     <<<<<<<<<<<<<<
    -0.81
     Fielding
    -0.80
    IndentedString
    -0.77
    .*")]
    -0.75
    ***************
    -0.74
     Beatrix
    -0.74
    PEZ
    -0.74
    POSITIVE LOGITS
     sure
    1.01
     SURE
    1.01
     Sure
    0.84
    sure
    0.81
    Sure
    0.80
    footed
    0.71
     sur
    0.69
    ècie
    0.68
    er
    0.68
     sicher
    0.66
    Act Density 0.071%

    No Known Activations