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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight differences or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patria
    -0.71
    onix
    -0.70
    bufio
    -0.70
     Melayu
    -0.69
     HSP
    -0.69
     Bier
    -0.68
     ostavi
    -0.68
     Jeong
    -0.67
    ěte
    -0.65
    ous
    -0.63
    POSITIVE LOGITS
     THAN
    1.95
     than
    1.77
     Than
    1.59
    Than
    1.52
    THAN
    1.35
    than
    1.31
     än
    1.26
     niż
    1.18
     decât
    1.18
     než
    1.16
    Act Density 0.149%

    No Known Activations