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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.57
    __":
    -0.51
     Hora
    -0.51
    __":
    -0.47
     toArray
    -0.46
    ::~
    -0.43
     $:$
    -0.42
    lück
    -0.42
    ilerini
    -0.41
    spra
    -0.41
    POSITIVE LOGITS
     cardiaque
    0.74
     uttered
    0.71
     חיצוניים
    0.70
    RTEX
    0.68
    extAlignment
    0.67
     InputDecoration
    0.66
     Followed
    0.66
     dedans
    0.65
     scattata
    0.65
    这句话
    0.64
    Act Density 0.271%

    No Known Activations