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

    Neuronpedia

    INDEX
    Explanations

    the word "propose" followed by an action or suggestion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "propose" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.69
    san
    -0.68
    kai
    -0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    iami
    -0.67
    oyal
    -0.67
    isol
    -0.67
    aver
    -0.66
    cross
    -0.64
    oa
    -0.64
    POSITIVE LOGITS
     propose
    1.07
     proposing
    1.01
    interstitial
    0.99
     proposes
    0.96
     proposals
    0.92
     proposal
    0.85
     proposed
    0.79
    entious
    0.76
    ĸļ
    0.76
    CHAT
    0.74
    Act Density 0.009%

    No Known Activations