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

    Neuronpedia

    INDEX
    Explanations

    affirmations or agreements in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abra
    -0.16
    ationToken
    -0.15
    uner
    -0.14
    aska
    -0.14
    unya
    -0.14
    adlo
    -0.14
    urrence
    -0.14
    akk
    -0.14
     Äijâu
    -0.14
    deal
    -0.14
    POSITIVE LOGITS
     indeed
    0.28
    inde
    0.25
    Indeed
    0.22
     Indeed
    0.21
     definitely
    0.17
    ãģ§ãģĻãģŃ
    0.16
    arend
    0.15
     Hlav
    0.15
     Amen
    0.15
    ç¡®
    0.15
    Act Density 0.151%

    No Known Activations