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

    Neuronpedia

    INDEX
    Explanations

    words indicating necessity and urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.23
     itself
    -0.15
    undry
    -0.15
    arti
    -0.14
    alm
    -0.14
    â
    -0.14
     Morr
    -0.13
    oui
    -0.13
    磨
    -0.13
    ags
    -0.13
    POSITIVE LOGITS
     yourself
    0.40
     yourselves
    0.31
     Yourself
    0.27
     your
    0.24
    your
    0.23
    ä½łçļĦ
    0.22
     можеÑĤе
    0.21
    Your
    0.19
    rott
    0.16
    ırak
    0.16
    Act Density 1.414%

    No Known Activations