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

    Neuronpedia

    INDEX
    Explanations

    countries, chemicals, and programs related to different subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drive
    -0.75
    body
    -0.73
    icum
    -0.72
    rip
    -0.71
    wan
    -0.70
    was
    -0.67
    dr
    -0.66
    orer
    -0.66
    iance
    -0.65
    istical
    -0.64
    POSITIVE LOGITS
     grouped
    1.15
     legion
    1.02
     listed
    1.01
     summarized
    0.96
     staples
    0.94
    senal
    0.84
     clustered
    0.84
     ones
    0.82
    :-
    0.82
     outlined
    0.80
    Act Density 0.276%

    No Known Activations