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

    Neuronpedia

    INDEX
    Explanations

    specific months and years

    oai_token-act-pair · gpt-3.5-turbo

    specific months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bidder
    -0.73
     continu
    -0.71
     stead
    -0.66
     phr
    -0.63
     newcom
    -0.62
     concession
    -0.61
     subscript
    -0.61
     latent
    -0.60
     promoter
    -0.60
    tro
    -0.59
    POSITIVE LOGITS
    -'
    0.76
    ibe
    0.73
    ulhu
    0.68
    iren
    0.68
     respectively
    0.67
    ame
    0.67
    ruary
    0.66
    illi
    0.65
    mort
    0.65
    isel
    0.65
    Act Density 0.118%

    No Known Activations