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

    Neuronpedia

    INDEX
    Explanations

    instances of direct speech and personal statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.30
     âĢŀ
    -0.26
     (“
    -0.23
     “[
    -0.23
     ``
    -0.19
    ãĢĮãģĤ
    -0.18
     “âĢ¦
    -0.18
     ”
    -0.16
     ãĢĮ
    -0.16
    ãĢĮãģĬ
    -0.15
    POSITIVE LOGITS
    bsite
    0.31
    apons
    0.29
    gnore
    0.28
    gether
    0.26
    crease
    0.24
    ir
    0.23
    ory
    0.21
    adays
    0.21
    tempts
    0.20
    ORY
    0.19
    Act Density 0.123%

    No Known Activations