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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and writing credits

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

    authorship attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.53
     ControllerBase
    -0.50
    quelize
    -0.49
    angliski
    -0.48
    stool
    -0.47
    lax
    -0.45
    Tikang
    -0.45
    presto
    -0.44
    obao
    -0.43
    httphttps
    -0.43
    POSITIVE LOGITS
    Written
    1.34
     Written
    1.14
     written
    0.92
    written
    0.86
     WRITTEN
    0.83
    Escrito
    0.82
     escritas
    0.63
     escrito
    0.63
     authored
    0.61
     rewritten
    0.60
    Act Density 0.038%

    No Known Activations