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

    Neuronpedia

    INDEX
    Explanations

    questions marked by a question mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.82
    ©¶æ
    -0.80
     unbeliev
    -0.71
     confir
    -0.70
     mutually
    -0.69
     spons
    -0.69
     rein
    -0.69
     encount
    -0.68
    aku
    -0.68
     ingest
    -0.68
    POSITIVE LOGITS
     Surely
    1.15
     Where
    1.13
     Well
    1.10
     Answer
    1.05
     Certainly
    1.04
     Why
    1.04
     Probably
    1.03
     Does
    1.02
     What
    1.02
     Possibly
    1.00
    Act Density 0.078%

    No Known Activations