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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the occurrence of events for the first time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.57
    adaptiveStyles
    -0.55
    geslacht
    -0.46
    ✭✭
    -0.44
    Liefs
    -0.43
    Grüsse
    -0.42
    hicles
    -0.42
    }{*}{}
    -0.41
     Bioaccumulative
    -0.41
    Lycka
    -0.41
    POSITIVE LOGITS
     впервые
    0.67
     erstmals
    0.56
    首次
    0.49
     rare
    0.46
     unprecedented
    0.45
     पह
    0.44
     inéd
    0.43
    rower
    0.43
    EndInit
    0.43
     popr
    0.43
    Act Density 0.292%

    No Known Activations