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

    Neuronpedia

    INDEX
    Explanations

    instances of emphatic punctuation or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iras
    -0.15
    uy
    -0.14
    undef
    -0.14
    inho
    -0.14
    akk
    -0.14
     Dabei
    -0.14
    rst
    -0.14
    ÑĢеÑĪ
    -0.14
    aris
    -0.14
    untas
    -0.14
    POSITIVE LOGITS
     nor
    0.54
     rather
    0.53
     Rather
    0.51
     Nor
    0.47
    Rather
    0.47
    rather
    0.46
    Nor
    0.43
    nor
    0.40
     sondern
    0.38
     بÙĦÚ©Ùĩ
    0.36
    Act Density 0.135%

    No Known Activations