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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "Through" and related variations indicating processes or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Salford
    -0.65
     heli
    -0.63
     Bayley
    -0.62
     Púb
    -0.62
     goud
    -0.61
     PUBL
    -0.61
    ässig
    -0.60
    Zem
    -0.60
     GNP
    -0.60
     AdapterView
    -0.59
    POSITIVE LOGITS
    Through
    2.41
     Through
    2.37
    through
    2.35
     through
    2.35
    THROUGH
    2.34
     THROUGH
    2.19
     thru
    1.87
     attraverso
    1.84
     través
    1.77
    thru
    1.72
    Act Density 0.109%

    No Known Activations