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

    Neuronpedia

    INDEX
    Explanations

    web-based media and news outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various media and news outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    proof
    -0.66
    bush
    -0.65
    tein
    -0.64
    tun
    -0.63
    potion
    -0.63
    CHAT
    -0.63
    0100
    -0.61
    ãĤ¯
    -0.59
    plane
    -0.58
    ty
    -0.58
    POSITIVE LOGITS
    hips
    1.12
    hops
    0.96
    chool
    0.90
    ystem
    0.84
    cale
    0.83
    hare
    0.83
    ettings
    0.80
    uggest
    0.80
    pring
    0.79
    hip
    0.79
    Act Density 0.338%

    No Known Activations