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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and online security risks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     extérieurs
    -0.66
    fjspx
    -0.64
     كومونز
    -0.63
     africains
    -0.63
    IsContent
    -0.62
     CreateTagHelper
    -0.62
    principalTable
    -0.61
    LookAnd
    -0.57
    GeoNames
    -0.56
    PhysRev
    -0.56
    POSITIVE LOGITS
     Den
    0.47
     Dietz
    0.47
     OMITTED
    0.47
    posedge
    0.47
    tauchen
    0.47
     presidency
    0.46
    Dowell
    0.46
    faz
    0.45
    enzi
    0.45
    aima
    0.44
    Act Density 0.263%

    No Known Activations