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

    Neuronpedia

    INDEX
    Explanations

    phrases that prompt the reader to subscribe or sign up

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the word "our"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Izan
    -0.81
    bender
    -0.78
    netflix
    -0.74
    yang
    -0.73
    ée
    -0.73
    lessness
    -0.71
    stood
    -0.71
    ivas
    -0.71
    nesota
    -0.71
    matter
    -0.71
    POSITIVE LOGITS
    selves
    1.01
     own
    0.93
     newest
    0.88
     latest
    0.86
     respective
    0.84
     sister
    0.81
     exclusive
    0.81
     motto
    0.80
     editorial
    0.79
     extensive
    0.78
    Act Density 0.068%

    No Known Activations