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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate capability or potential actions involving people and their choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.67
     Lives
    -0.55
     CURIAM
    -0.55
     mourut
    -0.55
     snippetHide
    -0.54
    syms
    -0.52
    IsContent
    -0.52
    UnitTesting
    -0.52
     Turning
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
     cross
    1.07
     travel
    1.02
     head
    1.02
     traverse
    0.90
     venture
    0.86
     enter
    0.77
    cross
    0.74
     journey
    0.73
     board
    0.72
     navigate
    0.71
    Act Density 0.410%

    No Known Activations