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

    Neuronpedia

    INDEX
    Explanations

    words related to concentrated focus or constraints

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concepts of confinement or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chev
    -0.90
    itsch
    -0.81
    WARD
    -0.62
     Uriel
    -0.61
     entitle
    -0.61
    \/\/
    -0.60
    uria
    -0.59
    osate
    -0.59
     adrenaline
    -0.57
    agara
    -0.57
    POSITIVE LOGITS
    ctions
    0.87
    ciating
    0.77
    gregation
    0.77
    ctory
    0.75
    uration
    0.74
    Sys
    0.74
    rency
    0.74
    enment
    0.74
    ption
    0.73
    ctive
    0.71
    Act Density 0.068%

    No Known Activations