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

    Neuronpedia

    INDEX
    Explanations

    keywords related to instructions and future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reh
    -0.15
    akit
    -0.15
    ãĥ©ãĥĥãĤ¯
    -0.14
    dge
    -0.14
    igon
    -0.14
    ereg
    -0.13
    aign
    -0.13
    krom
    -0.13
    Iso
    -0.13
    porate
    -0.13
    POSITIVE LOGITS
    .twitch
    0.15
    è¿«
    0.15
    zo
    0.15
    .scalablytyped
    0.14
    imas
    0.14
    éijij
    0.14
    ør
    0.14
    kle
    0.14
     Nice
    0.14
     posture
    0.13
    Act Density 0.017%

    No Known Activations