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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims regarding established facts or knowledge

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

    "It is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    It is followed by a statement of fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.08
     Theſe
    -0.86
     myſelf
    -0.85
     fubject
    -0.81
     ProtoMessage
    -0.76
     itſelf
    -0.75
     becauſe
    -0.72
     Jefus
    -0.69
    StreetMap
    -0.69
     raiſ
    -0.69
    POSITIVE LOGITS
     assumed
    0.64
     argued
    0.62
     noted
    0.59
     hypothesized
    0.57
     claimed
    0.55
     said
    0.55
     established
    0.53
     clear
    0.52
     decided
    0.52
     speculated
    0.50
    Act Density 0.296%

    No Known Activations