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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior actions or conditions

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

    sequences starting with before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.52
     étoient
    -0.51
     pleaſure
    -0.51
     Houſe
    -0.49
     Verſ
    -0.49
     Theſe
    -0.48
     Majefty
    -0.48
     noirs
    -0.46
     Eſ
    -0.45
     africaine
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.66
     subsequently
    0.64
     Rptr
    0.60
     Wicidata
    0.59
     eventually
    0.58
     being
    0.56
    MigrationBuilder
    0.56
     opting
    0.55
    Rptr
    0.54
    eventually
    0.54
    Act Density 0.015%

    No Known Activations