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

    Neuronpedia

    INDEX
    Explanations

    phrases related to growth or change over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating growth or change in various contexts, particularly negative trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aganda
    -0.70
    CHAT
    -0.65
     CLSID
    -0.63
    Ess
    -0.63
    Primary
    -0.63
    Kin
    -0.62
    Es
    -0.61
    Uh
    -0.60
    Chest
    -0.60
    iquette
    -0.60
    POSITIVE LOGITS
     dreamed
    0.84
    astical
    0.77
     imaginable
    0.77
    theless
    0.74
    vable
    0.71
     challeng
    0.68
     predic
    0.64
    eni
    0.64
    ancial
    0.62
    bilt
    0.62
    Act Density 0.071%

    No Known Activations