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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate future actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.84
     Efq
    -0.76
    UnusedPrivate
    -0.69
    GEBURTSDATUM
    -0.69
    ImageContext
    -0.67
    ंदीखरीदारी
    -0.65
    IndentedString
    -0.58
     actualmente
    -0.58
     Winf
    -0.57
     isSuccess
    -0.57
    POSITIVE LOGITS
     gladly
    0.67
    бливості
    0.65
     try
    0.64
     tạm
    0.61
     tentative
    0.61
    Begriffsklä
    0.61
     point
    0.60
    луй
    0.60
    try
    0.59
    ?}",
    0.58
    Act Density 0.100%

    No Known Activations