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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONCLUS
    -0.69
    ĵĺ
    -0.64
     dependence
    -0.64
     guiActiveUnfocused
    -0.62
     weakening
    -0.62
    Reward
    -0.61
     Nationwide
    -0.61
    Ĥ¬
    -0.60
     Improvement
    -0.59
     compromising
    -0.59
    POSITIVE LOGITS
    'd
    1.11
    zbollah
    1.10
    'll
    1.08
    pherd
    1.05
     joins
    1.02
     sits
    0.99
    resy
    0.96
     owns
    0.94
     wore
    0.94
    gemony
    0.93
    Act Density 0.250%

    No Known Activations