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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fixes
    -0.67
    Cho
    -0.64
    lights
    -0.64
    arthed
    -0.60
     Powered
    -0.58
    ULTS
    -0.57
     Returning
    -0.57
     Appears
    -0.57
     Compan
    -0.57
    cler
    -0.57
    POSITIVE LOGITS
     imagine
    1.25
     argue
    1.20
     bet
    1.16
    't
    1.07
     blame
    1.01
     expect
    0.99
     speculate
    0.95
     forgive
    0.93
     laugh
    0.90
     envision
    0.90
    Act Density 0.110%

    No Known Activations