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

    Neuronpedia

    INDEX
    Explanations

    discussions about social issues, specifically focusing on health, inequality, and structural challenges facing communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سع
    -0.50
     sáng
    -0.49
     memu
    -0.48
     aclar
    -0.48
     záz
    -0.47
     интер
    -0.47
    jans
    -0.46
    LLA
    -0.46
     ErrInvalid
    -0.46
     balle
    -0.45
    POSITIVE LOGITS
    Worse
    0.91
     Worse
    0.86
     worse
    0.85
     unknownFields
    0.78
     worst
    0.77
     unchecked
    0.77
     worsened
    0.76
     rampant
    0.76
     worsen
    0.74
    worse
    0.73
    Act Density 0.655%

    No Known Activations