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

    Neuronpedia

    INDEX
    Explanations

    the word "Furthermore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -1.03
    5
    -0.85
    ة
    -0.85
    os
    -0.85
    -
    -0.84
    1
    -0.83
    .
    -0.82
    ing
    -0.82
    6
    -0.79
    /
    -0.79
    POSITIVE LOGITS
    theless
    1.74
     Monfieur
    1.37
     myſelf
    1.36
     itſelf
    1.34
     ―――――
    1.34
     Forumite
    1.28
     Theſe
    1.26
     themſelves
    1.26
     himſelf
    1.24
     photolibrary
    1.23
    Act Density 0.182%

    No Known Activations