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

    Neuronpedia

    INDEX
    Explanations

    concepts related to motivation and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    refix
    -0.15
    este
    -0.14
    andWhere
    -0.14
    ongs
    -0.14
    alamat
    -0.14
    emm
    -0.14
    PLIC
    -0.14
    quer
    -0.14
     Richt
    -0.14
     Mix
    -0.13
    POSITIVE LOGITS
     vice
    0.23
    åħĪ
    0.21
     reverse
    0.21
     preced
    0.20
    reverse
    0.20
     preceded
    0.20
     first
    0.20
    Reverse
    0.19
     åħĪ
    0.19
    [::-
    0.19
    Act Density 0.203%

    No Known Activations