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

    Neuronpedia

    INDEX
    Explanations

    verbs connected to physical actions involving force or effort

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.92
    iband
    -0.77
    enta
    -0.73
    ipedia
    -0.72
    çĦ
    -0.71
    knit
    -0.71
    say
    -0.70
    variable
    -0.69
    brace
    -0.69
    OST
    -0.68
    POSITIVE LOGITS
     spree
    1.08
     extraord
    0.98
    tons
    0.96
     prowess
    0.93
     antics
    0.91
     frenzy
    0.87
     behaviour
    0.85
     habits
    0.84
     shenanigans
    0.83
     behaviours
    0.81
    Act Density 0.160%

    No Known Activations