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

    Neuronpedia

    INDEX
    Explanations

    proposals or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proposed" indicating suggestions or recommendations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scar
    -0.72
    seed
    -0.67
    gi
    -0.66
    san
    -0.66
    wood
    -0.65
    arta
    -0.65
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
     Hebdo
    -0.64
     Jude
    -0.64
    istics
    -0.64
    POSITIVE LOGITS
     proposals
    1.04
     proposed
    1.00
    interstitial
    1.00
     proposal
    0.96
    yout
    0.81
     proposes
    0.80
     proposing
    0.80
     Parenthood
    0.79
     propose
    0.78
     unnecess
    0.76
    Act Density 0.010%

    No Known Activations