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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" followed by further context

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.86
    ullivan
    -0.71
    aukee
    -0.70
    icut
    -0.69
    oser
    -0.65
    iped
    -0.65
    AZ
    -0.64
    oway
    -0.63
    YC
    -0.63
    izont
    -0.63
    POSITIVE LOGITS
     inval
    0.67
     there
    0.67
     whoever
    0.66
     justifies
    0.66
     contradicts
    0.63
     although
    0.63
     THERE
    0.62
     nobody
    0.62
     we
    0.62
     someone
    0.61
    Act Density 0.159%

    No Known Activations