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

    Neuronpedia

    INDEX
    Explanations

    proposals or suggestions for new projects or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clu
    -0.69
     kil
    -0.68
     Kl
    -0.64
    طق
    -0.64
     Mund
    -0.59
    ened
    -0.59
     Kers
    -0.58
    Lus
    -0.58
    </tr>
    -0.58
    Ethnicity
    -0.57
    POSITIVE LOGITS
     Proposals
    1.38
     proposals
    1.36
    POSAL
    1.29
    proposals
    1.29
     Proposal
    1.28
    Proposals
    1.26
     PROPOS
    1.25
    Proposal
    1.18
    PROPOSED
    1.18
     proposes
    1.18
    Act Density 0.106%

    No Known Activations