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

    Neuronpedia

    INDEX
    Explanations

    numerical references to buffer sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.81
    hig
    -0.78
    iple
    -0.67
    earable
    -0.66
    iamond
    -0.66
    ODUCT
    -0.64
    dfx
    -0.64
    IFA
    -0.64
    earch
    -0.63
    ideos
    -0.62
    POSITIVE LOGITS
     overflow
    1.29
     overfl
    1.05
     buffer
    0.82
    buffer
    0.81
     overrun
    0.77
     empt
    0.77
     zone
    0.71
    lot
    0.69
     blocker
    0.67
    bars
    0.67
    Act Density 0.009%

    No Known Activations