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

    Neuronpedia

    INDEX
    Explanations

    negations or words indicating the absence of something

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     indeed
    -0.75
     lots
    -0.73
    uanya
    -0.65
     Signalez
    -0.63
    enang
    -0.63
     any
    -0.62
    indeed
    -0.62
     gjø
    -0.60
     gedaan
    -0.60
    zegor
    -0.60
    POSITIVE LOGITS
     AssemblyCompany
    0.70
    Portail
    0.67
    CppCodeGen
    0.66
    UIControlState
    0.65
     Bertram
    0.65
    Vé
    0.63
    HandlerContext
    0.62
     voyageurs
    0.60
     McGowan
    0.60
     Wilber
    0.59
    Act Density 0.040%

    No Known Activations