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

    Neuronpedia

    INDEX
    Explanations

    complex phrases and mathematical notations related to functions and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.74
     lenker
    -0.72
    ITERATURE
    -0.70
     itſelf
    -0.70
     himſelf
    -0.69
    PRNewswire
    -0.69
     myſelf
    -0.69
     المعيارى
    -0.68
    +:+
    -0.67
    IBLIO
    -0.66
    POSITIVE LOGITS
    ,
    0.55
    !
    0.54
     if
    0.48
     when
    0.47
    ard
    0.46
    !,
    0.45
    如此
    0.45
     we
    0.44
     it
    0.44
    addContainerGap
    0.43
    Act Density 0.437%

    No Known Activations