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

    Neuronpedia

    INDEX
    Explanations

    words related to requests and feelings of obligation or gratitude in the context of creative work and personal interactions.

    oai_token-act-pair · gemini-2.0-flash

    emoticons and punctuation marks

    np_token-act-pair-logits · gpt-4o-mini

    emoticons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.76
     Waray
    -0.75
    发表于
    -0.73
     محفوظة
    -0.71
    RefNanny
    -0.68
    _();
    -0.67
    、“
    -0.66
    NUMX
    -0.66
    Tikang
    -0.66
    、【
    -0.65
    POSITIVE LOGITS
     :
    1.55
     :)
    1.16
     :(
    1.15
    :)
    1.14
     (:
    1.13
     :-
    1.07
    (:
    1.06
     :]
    1.05
     ;)
    1.03
    :(
    1.02
    Act Density 2.482%

    No Known Activations