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

    Neuronpedia

    INDEX
    Explanations

    checkboxes indicating human verification, likely part of a CAPTCHA system

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to verification and submission processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perspect
    -0.74
    ccording
    -0.74
     mathemat
    -0.65
    pread
    -0.63
    ufact
    -0.63
    ¥ŀ
    -0.59
     eleph
    -0.58
    vironment
    -0.56
     helic
    -0.56
     neighb
    -0.56
    POSITIVE LOGITS
     Invalid
    0.89
    box
    0.62
     Submit
    0.61
     button
    0.58
    interstitial
    0.57
    Submit
    0.55
    Capt
    0.55
    xon
    0.55
    qq
    0.55
    advertisement
    0.54
    Act Density 0.016%

    No Known Activations