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

    Neuronpedia

    INDEX
    Explanations

    direct speech or quotes from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.27
     âĢŀ
    -0.25
     “[
    -0.23
     (“
    -0.21
     “âĢ¦
    -0.18
     ``
    -0.16
    ãĢĮãģĤ
    -0.16
    iyim
    -0.15
    ñana
    -0.15
    بÙĪاسطة
    -0.15
    POSITIVE LOGITS
    ir
    0.36
    gether
    0.35
    bsite
    0.34
    adays
    0.33
    apons
    0.31
    ly
    0.27
    gnore
    0.27
    ory
    0.26
    tempts
    0.25
    crease
    0.25
    Act Density 0.173%

    No Known Activations