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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of quantity or limited availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wings
    -0.56
     Royal
    -0.55
    namespace
    -0.53
    Royal
    -0.53
    ρχ
    -0.52
     karar
    -0.48
     Ayala
    -0.48
    tières
    -0.48
    র্ব
    -0.48
     anew
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.84
     Hardly
    0.83
     Few
    0.80
     Rarely
    0.79
     kaum
    0.79
     snippetHide
    0.78
     hardly
    0.78
     weinig
    0.76
     Signalez
    0.75
     (\<
    0.75
    Act Density 0.209%

    No Known Activations