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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion and emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.70
    migrationBuilder
    -0.64
     թվական
    -0.61
    enderror
    -0.58
     AssemblyProduct
    -0.55
     "..\..\..\
    -0.54
    WSGI
    -0.52
     "..\..\
    -0.52
    исленность
    -0.52
    Sup
    -0.51
    POSITIVE LOGITS
     instantly
    0.74
     literally
    0.67
     absolutely
    0.66
     immediately
    0.66
     practically
    0.64
     litté
    0.61
     буквально
    0.59
     swear
    0.59
     instantaneously
    0.59
     Instantly
    0.58
    Act Density 0.262%

    No Known Activations