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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and similar prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yhte
    -0.34
     pelúcia
    -0.34
     appartiennent
    -0.33
     textes
    -0.32
     Técnica
    -0.31
     '\\;'
    -0.31
     Verhält
    -0.31
     peuples
    -0.31
     lunares
    -0.30
     uitgevoerd
    -0.30
    POSITIVE LOGITS
    complexContent
    0.77
    帖最后由
    0.76
     until
    0.73
     till
    0.70
    脚注の使い方
    0.69
     až
    0.68
     hasta
    0.66
     hanggang
    0.65
     &___
    0.63
     untill
    0.62
    Act Density 0.637%

    No Known Activations