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

    Neuronpedia

    INDEX
    Explanations

    references to bison and buffalo

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

    mammoth, bison, buffalo, rhino

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputModule
    -0.39
     Palt
    -0.37
     Bettina
    -0.36
     Rina
    -0.36
    providedIn
    -0.36
    Hentet
    -0.36
    __':
    -0.36
    latin
    -0.36
     Harry
    -0.36
    garn
    -0.35
    POSITIVE LOGITS
     bison
    1.60
     Bison
    1.50
     buffalo
    1.44
    buffalo
    1.23
     Buffalo
    1.03
    Buffalo
    1.02
    bison
    1.00
    🦬
    0.69
     Grizzly
    0.69
     BUFF
    0.65
    Act Density 0.004%

    No Known Activations