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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or groups of entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     all
    -0.20
    æīĢæľī
    -0.17
     various
    -0.15
     вÑģеÑħ
    -0.15
     Of
    -0.15
     wasn
    -0.15
    588
    -0.14
     Various
    -0.14
    onda
    -0.14
     itself
    -0.14
    POSITIVE LOGITS
     alike
    0.30
     respectively
    0.24
     respective
    0.21
     equally
    0.20
     Äijá»ģu
    0.19
     birden
    0.19
     separately
    0.18
     sets
    0.15
    chin
    0.15
    vero
    0.14
    Act Density 0.155%

    No Known Activations