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

    Neuronpedia

    INDEX
    Explanations

    references to unique or specific names and titles

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

    Follows names or titles, often initials

    np_acts-logits-general · gemini-2.0-flash

    thing called/named

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſever
    -1.17
     Anſ
    -1.08
     juſ
    -1.06
     Houſe
    -1.05
     Reſ
    -1.05
     itſelf
    -1.04
     houſe
    -1.03
     uſ
    -1.02
     Diſ
    -1.02
     ſche
    -1.01
    POSITIVE LOGITS
     R
    0.79
     K
    0.78
     The
    0.76
     S
    0.75
     Z
    0.74
     V
    0.74
     B
    0.72
     O
    0.72
     N
    0.71
     Green
    0.70
    Act Density 1.070%

    No Known Activations