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

    Neuronpedia

    INDEX
    Explanations

    questions related to processes and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <
    -0.50
    ater
    -0.48
    un
    -0.47
    cu
    -0.47
     croce
    -0.45
     lettres
    -0.45
     >
    -0.44
    he
    -0.44
    !
    -0.44
    غ
    -0.44
    POSITIVE LOGITS
     how
    1.49
     איך
    1.31
     कैसे
    1.31
    איך
    1.27
     cómo
    1.26
     hvordan
    1.23
     miten
    1.22
    cómo
    1.21
     Hvordan
    1.16
     HOW
    1.15
    Act Density 0.170%

    No Known Activations