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

    Neuronpedia

    INDEX
    Explanations

    the word "there" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of something or someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.73
     CJ
    -0.73
     cogn
    -0.69
     cent
    -0.62
     EC
    -0.61
     seat
    -0.59
     spinal
    -0.58
    Ctrl
    -0.57
     cups
    -0.57
    making
    -0.57
    POSITIVE LOGITS
    abouts
    1.15
     guiActiveUn
    0.93
    phabet
    0.89
    itia
    0.89
    upon
    0.88
    choes
    0.81
    ngth
    0.80
    leased
    0.80
    osher
    0.80
    zbollah
    0.79
    Act Density 0.040%

    No Known Activations