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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.88
    AutoScaleMode
    -0.84
    MLLoader
    -0.80
    DebuggerNonUser
    -0.80
     <=",
    -0.76
    NewUrlParser
    -0.73
    ]")]
    -0.72
     Normdatei
    -0.69
    ReusableCell
    -0.68
    ficulties
    -0.67
    POSITIVE LOGITS
     gotta
    0.71
     weren
    0.70
     folks
    0.69
     gonna
    0.69
     outta
    0.67
    Somebody
    0.65
    Gonna
    0.65
    ちゃった
    0.65
     somebody
    0.64
     wasn
    0.63
    Act Density 0.212%

    No Known Activations