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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the extent or scale of different situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the extent or magnitude of issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advertisement
    -0.74
    frog
    -0.72
    ools
    -0.72
    center
    -0.71
    wait
    -0.69
    cellaneous
    -0.69
    soDeliveryDate
    -0.68
    eka
    -0.67
    nis
    -0.66
    Center
    -0.64
    POSITIVE LOGITS
     devastation
    0.97
     damage
    0.96
     hostilities
    0.83
     difference
    0.82
     contamination
    0.82
     threat
    0.82
     injury
    0.81
     havoc
    0.80
     penetration
    0.79
     disruption
    0.79
    Act Density 0.136%

    No Known Activations