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

    Neuronpedia

    INDEX
    Explanations

    advertisements

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clus
    -0.78
    ties
    -0.71
    stood
    -0.70
    mate
    -0.68
     contingency
    -0.66
     sacr
    -0.66
     isolation
    -0.66
    cluded
    -0.65
    wald
    -0.64
     perspect
    -0.63
    POSITIVE LOGITS
     Advertisement
    0.93
     Continue
    0.89
    Advertisement
    0.86
    advertisement
    0.85
    Credit
    0.83
    Skip
    0.76
    Images
    0.73
    credit
    0.72
     Thumbnails
    0.69
    Image
    0.67
    Act Density 0.022%

    No Known Activations