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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions indicating decisions or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tensorflow
    -0.15
    regor
    -0.14
    orough
    -0.14
    ||||
    -0.14
    uales
    -0.14
    lÃŃn
    -0.14
    uco
    -0.14
    ùng
    -0.14
    ä¸ģ
    -0.14
    Ĥæķ°
    -0.13
    POSITIVE LOGITS
     noted
    0.24
     felt
    0.21
     argued
    0.20
     decided
    0.20
     hoped
    0.20
    ima
    0.20
     determined
    0.19
    felt
    0.19
     agreed
    0.19
     concluded
    0.19
    Act Density 0.077%

    No Known Activations