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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "ex-" indicating actions or conditions involving removal, separation, or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.59
    SharedCtor
    -0.58
     fubject
    -0.57
    ronpa
    -0.52
     المعيارى
    -0.51
    contentLoaded
    -0.51
     ModelExpression
    -0.50
     AssemblyCulture
    -0.50
    MessageState
    -0.50
    ſelf
    -0.50
    POSITIVE LOGITS
     Ex
    0.45
    Ex
    0.42
    ex
    0.40
     ex
    0.39
     GOLDEN
    0.34
    hili
    0.34
     boyfriend
    0.34
    chang
    0.33
     gr
    0.32
     Offic
    0.32
    Act Density 0.248%

    No Known Activations