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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight contrast or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    other than / aside from / apart from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __).
    -0.58
    oredCriteria
    -0.55
    Personensuche
    -0.52
     cim
    -0.49
     cul
    -0.49
     PeEnEo
    -0.48
    المكان
    -0.48
     lul
    -0.47
    AddTagHelper
    -0.47
    ungsbedingungen
    -0.47
    POSITIVE LOGITS
    Aside
    0.62
     Aside
    0.60
     Wikiseite
    0.60
    Apart
    0.57
     aside
    0.57
     Ahnung
    0.54
     Apart
    0.53
    Besides
    0.51
     großartige
    0.49
     sonst
    0.48
    Act Density 0.019%

    No Known Activations