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

    Neuronpedia

    INDEX
    Explanations

    instances where the expression "Not that" is used

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that begin with the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.81
    izont
    -0.75
    姫
    -0.71
    aciously
    -0.70
    pez
    -0.69
    utical
    -0.68
    00007
    -0.65
    kamp
    -0.64
    byn
    -0.63
    melon
    -0.63
    POSITIVE LOGITS
     anymore
    1.03
     anyone
    1.01
     anybody
    0.96
     bothered
    0.81
     they
    0.77
     nor
    0.77
     there
    0.76
    soever
    0.75
     any
    0.75
     uncommon
    0.74
    Act Density 0.064%

    No Known Activations