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

    Neuronpedia

    INDEX
    Explanations

    references to counterparts or comparisons between similar entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     },
    -0.65
    schra
    -0.65
    .'</
    -0.64
    }{%
    -0.61
    icycles
    -0.61
    imental
    -0.60
     sobran
    -0.59
    TextBoxColumn
    -0.58
    ##
    -0.58
     }</
    -0.57
    POSITIVE LOGITS
     counterparts
    1.23
     counterpart
    1.21
     successor
    0.85
     equivalents
    0.83
     successors
    0.78
     predecess
    0.77
     companion
    0.71
    part
    0.69
    +#+
    0.69
     predecessor
    0.68
    Act Density 0.008%

    No Known Activations