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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocacy and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certain
    -0.17
    506
    -0.15
    Notifier
    -0.14
    rans
    -0.14
     Brom
    -0.14
    udge
    -0.14
     itself
    -0.14
    peare
    -0.14
     Wald
    -0.14
    rades
    -0.14
    POSITIVE LOGITS
    åIJ§
    0.19
     yourself
    0.18
     your
    0.16
    най
    0.15
    oku
    0.15
    zell
    0.14
    ä½łçļĦ
    0.14
     yourselves
    0.14
    ÙĪÙĦÙĪ
    0.14
    uru
    0.14
    Act Density 0.547%

    No Known Activations