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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decidedly
    -0.57
    typically
    -0.54
     ostensibly
    -0.46
    essentially
    -0.44
    Toponymie
    -0.43
    Typically
    -0.43
     typically
    -0.42
     auroit
    -0.42
    неопр
    -0.42
    برگ
    -0.41
    POSITIVE LOGITS
     equipments
    0.61
     stuffs
    0.59
     own
    0.50
    SizeMode
    0.48
     defaultstate
    0.48
     every
    0.47
     performances
    0.46
     candidature
    0.45
     another
    0.45
     condition
    0.43
    Act Density 0.242%

    No Known Activations