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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate visibility or observation of data or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.51
     betweenstory
    -0.47
     transfieras
    -0.45
    MIDDLEWARE
    -0.44
    GEBURTSDATUM
    -0.43
    gof
    -0.42
    erton
    -0.42
    stor
    -0.42
     ventri
    -0.41
    cerpt
    -0.41
    POSITIVE LOGITS
     claramente
    0.57
     clearly
    0.57
    Clearly
    0.54
     Clearly
    0.51
    clearly
    0.50
     jelas
    0.50
    DockStyle
    0.50
     evident
    0.50
    idać
    0.50
     widać
    0.49
    Act Density 0.239%

    No Known Activations