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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "going" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aska
    -0.16
     handy
    -0.14
     Grat
    -0.14
    enko
    -0.14
    aro
    -0.14
     patron
    -0.13
    çĬ¬
    -0.13
    олом
    -0.13
    inger
    -0.13
    ensing
    -0.13
    POSITIVE LOGITS
    jak
    0.17
    echa
    0.15
    út
    0.15
    eu
    0.15
    ãĥ¼ãĥģ
    0.14
     chung
    0.14
    liers
    0.14
    osg
    0.14
    orks
    0.14
    eyse
    0.14
    Act Density 0.036%

    No Known Activations