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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving an impact or impression

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating absence, vacancy, or a negative impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uits
    -0.75
     Frequency
    -0.67
    GW
    -0.67
    scl
    -0.66
    alth
    -0.66
     Telesc
    -0.64
    FactoryReloaded
    -0.63
    anta
    -0.63
    Attempts
    -0.62
    adian
    -0.61
    POSITIVE LOGITS
     footprints
    1.25
     impression
    1.22
     imprint
    1.21
     residue
    1.18
     trail
    1.18
     mark
    1.14
     scars
    1.14
     gaping
    1.11
     voic
    1.07
     footprint
    1.02
    Act Density 0.120%

    No Known Activations