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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the impact of various actions or events

    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
    -0.76
    IDES
    -0.74
    corn
    -0.70
     Alps
    -0.69
    Plot
    -0.69
     Bav
    -0.67
    paces
    -0.67
    Pr
    -0.66
     whisk
    -0.66
     Rhythm
    -0.63
    POSITIVE LOGITS
     impact
    1.20
     impacts
    1.02
    impact
    1.02
    alore
    0.82
     crater
    0.81
    effects
    0.81
    ful
    0.81
    eless
    0.80
    iveness
    0.79
     impacted
    0.76
    Act Density 0.018%

    No Known Activations