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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing exclusivity or singling out something specific

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "only"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    communication
    -0.64
    insula
    -0.63
    actionDate
    -0.62
    imm
    -0.60
     pent
    -0.59
    pron
    -0.59
    went
    -0.57
     demolition
    -0.57
    osc
    -0.57
     nucleus
    -0.57
    POSITIVE LOGITS
     Only
    0.78
    teen
    0.75
    ices
    0.71
     incidentally
    0.68
     marginally
    0.68
    heses
    0.66
    soever
    0.66
    Corp
    0.66
    eus
    0.65
     Lives
    0.65
    Act Density 0.007%

    No Known Activations