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

    Neuronpedia

    INDEX
    Explanations

    quotes and statements expressing opinions or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.24
     âĢŀ
    -0.21
     “[
    -0.19
    ãĢĮãģĤ
    -0.18
     ``
    -0.16
    ãĢĮãģĬ
    -0.15
     (“
    -0.15
     “âĢ¦
    -0.14
    “We
    -0.14
    tte
    -0.14
    POSITIVE LOGITS
    gnore
    0.27
    bsite
    0.26
    apons
    0.26
    gether
    0.22
    ir
    0.22
    adays
    0.20
    crease
    0.18
    tempts
    0.18
    ","","
    0.17
    bove
    0.16
    Act Density 0.103%

    No Known Activations