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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks, indicating dialogue or quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.99
     Efq
    -0.93
    ?''
    -0.92
     Infórmanos
    -0.87
     Telex
    -0.84
     Lio
    -0.82
    ***********/
    -0.79
    -------------</
    -0.79
     Tio
    -0.79
    theless
    -0.78
    POSITIVE LOGITS
    ‘
    1.63
     ‚
    1.35
     ‘
    1.34
    ‗
    1.21
    ‘‘
    0.97
    …..
    0.87
    ……
    0.82
     ‘‘
    0.82
    〝
    0.81
    .’
    0.79
    Act Density 0.173%

    No Known Activations