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

    Neuronpedia

    INDEX
    Explanations

    noun phrases that indicate importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.86
    цездатний
    -0.73
    featureID
    -0.73
    tagHelperRunner
    -0.68
     kaynağından
    -0.65
     betweenstory
    -0.63
    orghini
    -0.62
     beginnetje
    -0.62
    -0.62
     estekak
    -0.61
    POSITIVE LOGITS
    GraphicsUnit
    0.51
     []:
    0.51
     Leg
    0.49
     '{@
    0.46
    espère
    0.46
     leg
    0.45
    devise
    0.44
    Leg
    0.44
    opal
    0.44
     tied
    0.43
    Act Density 0.380%

    No Known Activations