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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and forms of the verb "to be," indicating necessity or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    popper
    -0.58
     alber
    -0.57
     messing
    -0.56
    Sucesor
    -0.55
    expandindo
    -0.54
     tarda
    -0.54
    +#+#
    -0.51
     MEAN
    -0.51
     capitalization
    -0.51
    flap
    -0.50
    POSITIVE LOGITS
     οποία
    0.82
    خرى
    0.74
    ನ್ನು
    0.68
     οποίο
    0.67
    LookAnd
    0.66
    MethodManager
    0.65
    "):
    0.64
    ponses
    0.64
    다고
    0.64
     conducta
    0.63
    Act Density 0.754%

    No Known Activations