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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate new developments or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irs
    -0.17
    tas
    -0.15
    .ua
    -0.15
     automáticamente
    -0.15
    ssp
    -0.15
    erland
    -0.14
     automát
    -0.14
    clud
    -0.14
    ord
    -0.14
    à¥įफ
    -0.14
    POSITIVE LOGITS
    anders
    0.15
    amet
    0.15
    iano
    0.15
     nutshell
    0.15
    rafted
    0.14
     Notre
    0.14
    unker
    0.14
    urther
    0.14
    lick
    0.14
    ابÙĩ
    0.14
    Act Density 0.044%

    No Known Activations