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

    Neuronpedia

    INDEX
    Explanations

    superlatives or nouns that indicate a unique or exceptional position

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    des
    -0.74
    ends
    -0.71
    rawl
    -0.67
    md
    -0.66
    iety
    -0.66
    ence
    -0.65
    ruary
    -0.64
    abuse
    -0.63
    cart
    -0.63
    de
    -0.63
    POSITIVE LOGITS
     thing
    0.97
     surviving
    0.90
     remaining
    0.89
     conceivable
    0.88
     drawback
    0.84
     reason
    0.82
     obstacle
    0.81
     extant
    0.81
     beneficiary
    0.79
     way
    0.77
    Act Density 0.030%

    No Known Activations