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

    Neuronpedia

    INDEX
    Explanations

    phrases that express contradictions or ambiguity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anka
    -0.19
    aira
    -0.15
     ARGS
    -0.15
    æĸ¯çī¹
    -0.14
    adık
    -0.14
     å¾Ĵ
    -0.14
    isu
    -0.13
    Ĺ
    -0.13
    pton
    -0.13
    ivid
    -0.13
    POSITIVE LOGITS
     implies
    0.39
     imply
    0.39
     implication
    0.38
     suggest
    0.36
     implied
    0.36
     suggestion
    0.35
     hint
    0.35
     suggests
    0.34
     implying
    0.34
     ins
    0.33
    Act Density 0.277%

    No Known Activations