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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subscription services and terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subscriptions and newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -1.00
     Lank
    -0.72
    cair
    -0.70
    uador
    -0.69
    adish
    -0.68
     myself
    -0.68
    ndra
    -0.68
    aples
    -0.67
    berra
    -0.67
    keley
    -0.66
    POSITIVE LOGITS
     woes
    0.92
    ivery
    0.69
     antics
    0.68
     namesake
    0.67
    iest
    0.66
     counterpart
    0.66
     holdings
    0.66
     exploits
    0.65
     counterparts
    0.64
     cousin
    0.63
    Act Density 0.439%

    No Known Activations