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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey encouragement or support for ongoing efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лÑĥг
    -0.17
    öh
    -0.15
     Wahl
    -0.15
    ché
    -0.14
     Monter
    -0.14
    ullen
    -0.14
     reminded
    -0.13
    oly
    -0.13
    .ascii
    -0.13
    CHA
    -0.13
    POSITIVE LOGITS
     continuation
    0.36
     continue
    0.35
     continues
    0.35
    continue
    0.34
     trend
    0.33
     continued
    0.33
    	continue
    0.30
     continuing
    0.30
    继ç»Ń
    0.28
     continu
    0.28
    Act Density 0.171%

    No Known Activations