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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used to draw comparisons or highlight conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    00007
    -0.74
    oway
    -0.66
    aster
    -0.63
     @@
    -0.59
    Winged
    -0.58
    :'
    -0.56
    legram
    -0.56
    :[
    -0.56
    +.
    -0.54
    ounding
    -0.54
    POSITIVE LOGITS
     advertised
    0.93
     evidenced
    0.88
     planned
    0.88
     hoped
    0.88
     opposed
    0.87
     claimed
    0.87
    pired
    0.85
     intended
    0.81
     usual
    0.80
     contemplated
    0.79
    Act Density 0.099%

    No Known Activations