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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apologised
    -0.70
     ProtoMessage
    -0.69
    Portale
    -0.68
     apologise
    -0.67
     stupid
    -0.67
     shitty
    -0.67
     wierd
    -0.66
     weird
    -0.65
     насељу
    -0.63
     crazy
    -0.63
    POSITIVE LOGITS
    ]),
    0.80
    FormTagHelper
    0.70
     which
    0.65
    }';
    0.59
    ]))
    0.58
    ]";
    0.57
    beforeSend
    0.55
    où
    0.54
    which
    0.54
     that
    0.53
    Act Density 0.503%

    No Known Activations