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

    Neuronpedia

    INDEX
    Explanations

    mentions of information technology (IT)

    oai_token-act-pair · gpt-3.5-turbo

    references to the IT (Information Technology) industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥ³
    -0.75
    toggle
    -0.72
    ktop
    -0.69
    ãĥĸ
    -0.68
     [|
    -0.68
    ãĥł
    -0.67
    ãĤ¯
    -0.64
    ãĥģ
    -0.63
    ãĥķãĤ©
    -0.62
     unrestricted
    -0.62
    POSITIVE LOGITS
    IME
    1.04
    EMS
    0.96
    rehensive
    0.89
    TO
    0.85
    MIN
    0.84
    ARI
    0.84
    ILA
    0.79
    AC
    0.79
    IDE
    0.79
    ython
    0.79
    Act Density 0.015%

    No Known Activations