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

    Neuronpedia

    INDEX
    Explanations

    references to mixed populations or varying combinations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ount
    -0.62
    дарь
    -0.58
     tố
    -0.57
     Gost
    -0.56
    ModelForm
    -0.52
    bildung
    -0.52
    ators
    -0.51
     OMIT
    -0.50
    achuca
    -0.50
    Tikang
    -0.50
    POSITIVE LOGITS
     mixed
    1.30
     combined
    1.29
     coupled
    1.29
     Combined
    1.25
     Coupled
    1.17
    combined
    1.16
     paired
    1.15
    mixed
    1.15
    Combined
    1.14
     Mixed
    1.12
    Act Density 0.239%

    No Known Activations