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

    Neuronpedia

    INDEX
    Explanations

    the name "Ed" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.80
    =-=-
    -0.70
    Ĥİ
    -0.66
    othal
    -0.66
    falls
    -0.66
    TY
    -0.65
    cffffcc
    -0.65
     à¨
    -0.65
     shotguns
    -0.64
     Helsinki
    -0.64
    POSITIVE LOGITS
    gew
    1.12
    mund
    1.12
    dy
    1.05
    itions
    1.04
    ifice
    1.03
    monton
    1.02
    ricks
    0.99
    ison
    0.99
    ges
    0.98
    pires
    0.98
    Act Density 0.014%

    No Known Activations