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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant statements or remarks

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing significant declarations or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wagon
    -0.71
     trail
    -0.69
     posit
    -0.69
     bounds
    -0.69
     pigeon
    -0.69
     Canter
    -0.67
     duel
    -0.67
     Mirage
    -0.66
     trainer
    -0.66
     Bangkok
    -0.66
    POSITIVE LOGITS
    there
    1.03
    while
    0.99
    Clearly
    0.97
    everyone
    0.96
    Unfortunately
    0.95
    ï¸ı
    0.94
    Companies
    0.94
    particularly
    0.93
    Today
    0.93
    ccording
    0.93
    Act Density 0.157%

    No Known Activations