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

    Neuronpedia

    INDEX
    Explanations

    references to books or reading-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippers
    -0.19
    curity
    -0.15
    usercontent
    -0.15
    allon
    -0.15
    ãĤĮãģ©
    -0.15
    orsk
    -0.15
    appers
    -0.14
    ilded
    -0.14
     Kron
    -0.14
    adge
    -0.14
    POSITIVE LOGITS
    ends
    0.25
    worm
    0.24
     Depos
    0.23
    shelf
    0.21
     traversal
    0.21
    keeping
    0.20
    lice
    0.20
    wy
    0.19
    lover
    0.19
    ended
    0.18
    Act Density 0.017%

    No Known Activations