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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "there" followed by descriptions or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "there" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CJ
    -0.69
     ±
    -0.63
     actionGroup
    -0.62
     cogn
    -0.59
    ship
    -0.59
    sac
    -0.57
     tract
    -0.57
    ONSORED
    -0.57
    icial
    -0.57
    SB
    -0.56
    POSITIVE LOGITS
    abouts
    1.33
    upon
    1.16
    fore
    0.92
    FORE
    0.80
    choes
    0.80
    etheless
    0.75
    after
    0.73
    hovah
    0.73
    phabet
    0.71
    ngth
    0.67
    Act Density 0.113%

    No Known Activations