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

    Neuronpedia

    INDEX
    Explanations

    names of organizations and entities across various sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.91
     GenerationType
    -0.87
    ConstraintMaker
    -0.86
    ItemBackground
    -0.83
    uxxxx
    -0.76
    цездатний
    -0.74
    InitStruct
    -0.73
    رشف
    -0.72
    IntoConstraints
    -0.67
     estekak
    -0.66
    POSITIVE LOGITS
    ändigt
    0.52
    both
    0.49
     run
    0.48
     both
    0.48
     jer
    0.47
    Run
    0.47
    rane
    0.46
    mim
    0.45
    之一
    0.45
    timo
    0.44
    Act Density 0.582%

    No Known Activations