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

    Neuronpedia

    INDEX
    Explanations

    the word "that" within various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "I think that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.69
    ãĥīãĥ©
    -0.67
    Guard
    -0.65
    feet
    -0.65
    hips
    -0.65
    orah
    -0.64
    iped
    -0.63
    istance
    -0.63
    ington
    -0.61
    IELD
    -0.61
    POSITIVE LOGITS
     contradicts
    0.82
     justifies
    0.76
    izoph
    0.72
     although
    0.71
     happened
    0.70
    cher
    0.69
     translates
    0.69
     qualifies
    0.69
     undermines
    0.68
     applies
    0.68
    Act Density 0.236%

    No Known Activations