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

    Neuronpedia

    INDEX
    Explanations

    percentage values and their related formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.76
    ^(@)
    -0.74
     defaultstate
    -0.74
     referenties
    -0.73
     esterni
    -0.71
     themſelves
    -0.71
    ⇑
    -0.70
     crdi
    -0.69
     pleaſure
    -0.69
     ſmall
    -0.69
    POSITIVE LOGITS
     %
    1.68
     %,
    1.00
     %)
    0.92
     %),
    0.81
     ContentValues
    0.81
     %.
    0.78
     #{
    0.76
     ')[
    0.70
    onnage
    0.68
     (;;
    0.67
    Act Density 0.135%

    No Known Activations