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

    Neuronpedia

    INDEX
    Explanations

    sentences with significant numerical values or high frequency indicating importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.96
    ReusableCell
    -0.91
     للمعارف
    -0.89
    <pad>
    -0.85
    <unused79>
    -0.85
    <unused47>
    -0.85
    <unused41>
    -0.85
     Infórmanos
    -0.85
    <unused52>
    -0.85
    <unused8>
    -0.85
    POSITIVE LOGITS
    ↵↵
    0.47
    The
    0.38
    Besides
    0.34
    Though
    0.33
    Furthermore
    0.32
    </u>
    0.31
    </i>
    0.31
     Besides
    0.30
     Though
    0.30
     The
    0.29
    Act Density 0.719%

    No Known Activations