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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Umgang
    -0.40
     Amts
    -0.37
     좋
    -0.35
    ︎
    -0.35
     decidió
    -0.35
     matters
    -0.33
     semula
    -0.33
     decidiu
    -0.33
     decidieron
    -0.32
     seuls
    -0.32
    POSITIVE LOGITS
     regard
    0.87
     recourse
    0.81
     hesitation
    0.77
     prejudice
    0.77
     exception
    0.73
     interruption
    0.72
     fanfare
    0.72
     fail
    0.71
     nonUne
    0.71
    regard
    0.69
    Act Density 0.266%

    No Known Activations