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

    Neuronpedia

    INDEX
    Explanations

    capitalized acronyms related to educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or title abbreviated as "CM."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.81
    rets
    -0.80
    ãĥ¼ãĥĨ
    -0.77
    lihood
    -0.76
    reys
    -0.73
    glers
    -0.72
     Machina
    -0.71
    ãĥ³ãĤ¸
    -0.71
    furt
    -0.69
    raltar
    -0.69
    POSITIVE LOGITS
    ODE
    0.88
    HC
    0.84
    CP
    0.82
    OS
    0.82
    OUNT
    0.80
     Punk
    0.79
    AMP
    0.77
    illon
    0.77
    VC
    0.76
    achine
    0.75
    Act Density 0.008%

    No Known Activations