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

    Neuronpedia

    INDEX
    Explanations

    references to collaboration or teamwork in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.57
    –
    -0.50
     Большая
    -0.50
    ’
    -0.47
     diſt
    -0.46
    -
    -0.45
     loob
    -0.45
     inſ
    -0.45
     tayo
    -0.44
     下午
    -0.44
    POSITIVE LOGITS
    évaluateur
    0.88
     Jr
    0.81
     <=",
    0.80
     \&
    0.72
    OOTDTY
    0.72
    ✨:
    0.71
     NSCoder
    0.71
     Roskov
    0.70
     et
    0.70
    bufio
    0.70
    Act Density 0.173%

    No Known Activations