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

    Neuronpedia

    INDEX
    Explanations

    common spokespeople phrases used for sharing stories or news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of requests or prompts to take action, particularly related to reading or sharing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bestos
    -0.82
    hower
    -0.78
    pect
    -0.75
    ħĭ
    -0.71
    ngth
    -0.69
    terior
    -0.69
    iversary
    -0.66
    ouls
    -0.64
    elli
    -0.64
    uga
    -0.64
    POSITIVE LOGITS
     Format
    0.68
     Pastebin
    0.65
    POL
    0.64
     Consent
    0.63
     Discuss
    0.63
    ...]
    0.63
     Share
    0.62
     Paste
    0.58
     Updated
    0.57
     share
    0.57
    Act Density 0.044%

    No Known Activations