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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to the impact of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "impact."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TERN
    -0.74
    corn
    -0.73
    IDES
    -0.70
     Bav
    -0.69
     Alps
    -0.68
    GE
    -0.66
     whisk
    -0.66
    Plot
    -0.66
    ago
    -0.66
    wagen
    -0.65
    POSITIVE LOGITS
     impact
    1.10
     impacts
    1.00
    impact
    0.98
     crater
    0.87
    ful
    0.86
    alore
    0.84
    eless
    0.82
    effects
    0.80
     impacted
    0.77
    uates
    0.76
    Act Density 0.022%

    No Known Activations