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

    Neuronpedia

    INDEX
    Explanations

    specific names and terms related to sports, entertainment, and military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ema
    -0.78
     Ponds
    -0.72
     Lansing
    -0.70
     ISU
    -0.69
    ModelMap
    -0.68
     Alam
    -0.66
     Sina
    -0.65
    naments
    -0.65
     Lizard
    -0.64
     Albright
    -0.64
    POSITIVE LOGITS
     Robson
    0.77
     throm
    0.71
     Atlas
    0.69
    ATLAS
    0.68
     surf
    0.68
     Blake
    0.67
     cocaine
    0.66
    EDEFAULT
    0.66
    Atlas
    0.65
    rus
    0.64
    Act Density 3.164%

    No Known Activations