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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proving something or having evidence to support a claim

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence or verification of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adish
    -0.77
    FP
    -0.70
    step
    -0.68
     newsletters
    -0.67
    artments
    -0.67
    artment
    -0.66
    hops
    -0.65
    letal
    -0.64
     contrace
    -0.63
     Peninsula
    -0.62
    POSITIVE LOGITS
     proven
    1.02
    proven
    0.81
    ãĥ¼ãĥĨ
    0.80
     proves
    0.78
     proved
    0.77
    \\\\\\\\
    0.76
    ingen
    0.75
     debunked
    0.73
    iary
    0.73
     discredited
    0.72
    Act Density 0.011%

    No Known Activations