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

    Neuronpedia

    INDEX
    Explanations

    words related to sharing or sending information electronically

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in new" along with other instances relating to numerical or countable references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.79
    emis
    -0.71
    etheless
    -0.70
     distances
    -0.69
    blance
    -0.67
    ibur
    -0.65
    PASS
    -0.65
    til
    -0.65
     detractors
    -0.64
    asks
    -0.64
    POSITIVE LOGITS
     accordance
    0.90
     conjunction
    0.86
     chronological
    0.85
     lieu
    0.81
     advance
    0.79
    PDATE
    0.78
    STRUCT
    0.75
    bound
    0.73
     Print
    0.72
     ital
    0.72
    Act Density 0.186%

    No Known Activations