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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hesitation and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.96
     nakalista
    -0.84
    SequentialGroup
    -0.78
    AxisAlignment
    -0.78
    MemoryWarning
    -0.78
    complexContent
    -0.78
    ContentAsync
    -0.76
    Hochspringen
    -0.75
    脚注の使い方
    -0.75
    /*
    -0.75
    POSITIVE LOGITS
     fast
    0.51
    iner
    0.47
    he
    0.45
     short
    0.45
     soon
    0.44
    */].
    0.44
     Short
    0.43
    Short
    0.42
    all
    0.42
    fast
    0.42
    Act Density 0.251%

    No Known Activations