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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in 'ly'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aily
    -0.74
    ilion
    -0.67
     Cause
    -0.67
     League
    -0.66
    Liter
    -0.66
    hao
    -0.65
    elope
    -0.64
    iens
    -0.63
    eer
    -0.63
    orem
    -0.63
    POSITIVE LOGITS
     positioned
    0.94
     situated
    0.93
     priced
    0.91
     housed
    0.89
     transitioned
    0.87
     formulated
    0.87
     marketed
    0.87
     separated
    0.86
     spaced
    0.84
     employed
    0.83
    Act Density 1.248%

    No Known Activations