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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, particularly auditoriums

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of buildings or facilities, particularly those ending in "ium."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĦ
    -0.78
     neut
    -0.77
     paralysis
    -0.74
    vernment
    -0.71
     Logged
    -0.68
     unpublished
    -0.65
     cryptoc
    -0.64
     reconnect
    -0.63
     filament
    -0.63
     competence
    -0.63
    POSITIVE LOGITS
    lain
    1.20
    tyard
    1.02
    stones
    0.85
    rooms
    0.84
    rats
    0.81
    goers
    0.81
    Initialized
    0.81
    nas
    0.80
    hare
    0.79
    gur
    0.79
    Act Density 0.120%

    No Known Activations