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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ηγ
    -0.16
    otti
    -0.15
    zung
    -0.15
    roz
    -0.14
     bì
    -0.14
    esub
    -0.14
     ch
    -0.14
    é
    -0.13
    wrapper
    -0.13
    صر
    -0.13
    POSITIVE LOGITS
    flate
    0.17
    ofi
    0.15
    òi
    0.15
     Colomb
    0.15
    olo
    0.15
    ande
    0.15
    Ô
    0.15
    egra
    0.14
    amic
    0.14
    idl
    0.14
    Act Density 0.082%

    No Known Activations