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

    Neuronpedia

    INDEX
    Explanations

    words related to personal developments and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to evaluating performance and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.80
    UTE
    -0.66
     femin
    -0.59
     Gender
    -0.59
    Gender
    -0.58
    interstitial
    -0.58
     dehuman
    -0.57
     fame
    -0.57
     mascul
    -0.55
    Joined
    -0.55
    POSITIVE LOGITS
     meantime
    0.79
     assurances
    0.75
    ivably
    0.74
     uncertainties
    0.72
     uncertainty
    0.71
    ebus
    0.69
     contingency
    0.68
    enario
    0.66
     caveats
    0.66
    pard
    0.65
    Act Density 1.263%

    No Known Activations