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

    Neuronpedia

    INDEX
    Explanations

    expressions related to recognition and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andel
    -0.17
    pell
    -0.17
    uria
    -0.15
    eh
    -0.15
    endar
    -0.14
    @example
    -0.14
    apl
    -0.14
    ؤ
    -0.14
    irit
    -0.13
    afi
    -0.13
    POSITIVE LOGITS
    称
    0.25
     called
    0.23
    稱
    0.23
    åı«
    0.21
    called
    0.21
     gá»įi
    0.19
    -called
    0.17
     наз
    0.17
     Called
    0.17
     name
    0.16
    Act Density 0.335%

    No Known Activations