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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imest
    -0.17
    IOUS
    -0.16
    bersome
    -0.16
    erman
    -0.15
    èĬĿ
    -0.15
    icter
    -0.15
    lernen
    -0.14
    ivas
    -0.14
    Violation
    -0.14
    ãĥ³ãĥĪ
    -0.14
    POSITIVE LOGITS
     natural
    0.51
     understandable
    0.46
    natural
    0.42
     Natural
    0.40
    Natural
    0.37
     logical
    0.37
     normal
    0.35
     reasonable
    0.34
     Understand
    0.32
     natur
    0.31
    Act Density 0.106%

    No Known Activations