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

    Neuronpedia

    INDEX
    Explanations

    terms related to a broad variety of subjects and topics, focusing in particular on classifications and comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intende
    -0.52
    MatIconModule
    -0.52
     faceva
    -0.52
     svolge
    -0.51
     frappé
    -0.51
     quitt
    -0.50
     Septembre
    -0.49
     voleva
    -0.49
     aspetta
    -0.48
     Novembre
    -0.48
    POSITIVE LOGITS
     range
    1.43
     Range
    1.36
     RANGE
    1.35
     ranges
    1.32
    range
    1.29
     Ranges
    1.25
    Range
    1.25
    RANGE
    1.20
    ranges
    1.15
     ranged
    1.09
    Act Density 0.086%

    No Known Activations