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

    Neuronpedia

    INDEX
    Explanations

    the word "when" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agini
    -0.17
    gil
    -0.17
    isu
    -0.16
    adaÅŁ
    -0.16
    AFX
    -0.15
    unately
    -0.15
    onde
    -0.15
    anela
    -0.15
    assin
    -0.15
    adele
    -0.14
    POSITIVE LOGITS
    soever
    0.24
    /if
    0.22
    abouts
    0.19
    -либо
    0.19
    -нибÑĥдÑĮ
    0.18
    ev
    0.16
    upon
    0.16
     respect
    0.15
     it
    0.15
     they
    0.15
    Act Density 0.131%

    No Known Activations