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

    Neuronpedia

    INDEX
    Explanations

    words related to physical positions and movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivals
    -0.94
     Ends
    -0.85
     Critics
    -0.77
    rates
    -0.76
    ologies
    -0.75
    sonian
    -0.75
    olutions
    -0.74
    ieties
    -0.74
    osate
    -0.73
     Cases
    -0.73
    POSITIVE LOGITS
     wearing
    1.48
     dressed
    1.43
     grinning
    1.43
     kneeling
    1.39
     staring
    1.38
     smiling
    1.37
     clutching
    1.36
     clad
    1.35
     sweating
    1.30
     gazing
    1.27
    Act Density 0.230%

    No Known Activations