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

    Neuronpedia

    INDEX
    Explanations

    the word "there" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CJ
    -0.65
    ME
    -0.62
     Buck
    -0.60
    ONSORED
    -0.59
     Slayer
    -0.59
     HIM
    -0.59
     scoop
    -0.57
     Heights
    -0.57
     Khe
    -0.56
     Mecca
    -0.56
    POSITIVE LOGITS
    abouts
    1.50
    upon
    1.18
    fore
    0.91
    FORE
    0.79
    olver
    0.74
    idel
    0.74
    onian
    0.71
    idents
    0.71
     guiActiveUn
    0.71
    ngth
    0.71
    Act Density 0.120%

    No Known Activations