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

    Neuronpedia

    INDEX
    Explanations

    references to key individuals or entities within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.77
     Arden
    -0.75
    .*")]
    -0.74
     Berna
    -0.74
    Parcelize
    -0.69
    stateProvider
    -0.68
     cref
    -0.67
    льки
    -0.67
     ")";
    -0.66
     dvs
    -0.66
    POSITIVE LOGITS
     Moos
    1.05
    Coo
    1.03
     Nook
    1.01
     Cooley
    0.96
     hoo
    0.95
    oob
    0.93
    Doo
    0.93
     Hoo
    0.91
     Dooley
    0.91
     hoops
    0.89
    Act Density 0.163%

    No Known Activations