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

    Neuronpedia

    INDEX
    Explanations

    the adverb "simply" and its variations, indicating a focus on straightforwardness or clarity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISupport
    -0.94
     passim
    -0.77
    arote
    -0.71
     culturelles
    -0.71
     regardant
    -0.71
    sard
    -0.71
     féminin
    -0.70
     Packard
    -0.68
     Gallardo
    -0.68
     atteinte
    -0.67
    POSITIVE LOGITS
     Simply
    1.06
    Simply
    1.03
     simply
    0.94
    simpleType
    0.94
    simply
    0.91
    PLY
    0.90
    er
    0.81
     SIMPLE
    0.81
    Sole
    0.80
    Einfach
    0.80
    Act Density 0.083%

    No Known Activations