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

    Neuronpedia

    INDEX
    Explanations

    dates and time references

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antz
    -0.71
    itus
    -0.70
    ivas
    -0.69
    ventures
    -0.66
    APTER
    -0.66
    ibl
    -0.66
    ward
    -0.65
    ben
    -0.65
    worn
    -0.64
    pointers
    -0.64
    POSITIVE LOGITS
     vicinity
    1.31
     meantime
    1.09
     same
    1.07
     midst
    1.01
     Philippines
    1.00
     context
    0.96
     guise
    0.96
     shortest
    0.94
     ballpark
    0.92
     foreseeable
    0.91
    Act Density 0.268%

    No Known Activations