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

    Neuronpedia

    INDEX
    Explanations

    phrases that express doubt or uncertainty regarding someone's competency or credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uncertainty or disbelief

    np_acts-logits-general · gemini-2.0-flash

    call into question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.65
    MessageOf
    -0.63
    CodedInputStream
    -0.63
    StructEnd
    -0.62
     otomatig
    -0.61
     InputDecoration
    -0.57
     itſelf
    -0.56
    AndEndTag
    -0.56
     beginnetje
    -0.54
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
     doubt
    2.40
     doubts
    2.15
    doubt
    1.99
     doubted
    1.88
     doubtful
    1.85
     Doubt
    1.85
    Doubt
    1.72
     doute
    1.63
     doubting
    1.63
     сом
    1.53
    Act Density 0.330%

    No Known Activations