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

    Neuronpedia

    INDEX
    Explanations

    appeals for financial support or donations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to donations and support for causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equilibrium
    -0.64
     Poles
    -0.59
     hallucinations
    -0.57
     interpreted
    -0.57
     surfaces
    -0.57
     Fou
    -0.56
     orth
    -0.55
    Exactly
    -0.55
     angles
    -0.54
    pects
    -0.54
    POSITIVE LOGITS
     Subscribe
    0.92
     coupon
    0.87
     Patreon
    0.86
    istration
    0.86
     bookmark
    0.86
     subscribe
    0.85
     ðŁij
    0.84
    Subscribe
    0.84
     subscribing
    0.82
     Membership
    0.81
    Act Density 0.347%

    No Known Activations