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

    Neuronpedia

    INDEX
    Explanations

    email addresses and usernames

    oai_token-act-pair · gpt-3.5-turbo

    elements related to contact information and referrals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IRA
    -0.66
     Friendship
    -0.61
     Pillar
    -0.61
     Opposition
    -0.60
     recourse
    -0.59
     Championship
    -0.59
     Throne
    -0.59
     subsistence
    -0.58
     Allied
    -0.58
     Yuan
    -0.58
    POSITIVE LOGITS
    @
    0.88
    ickr
    0.78
    racuse
    0.74
    fw
    0.74
    jc
    0.73
    stats
    0.72
    cmd
    0.72
    _
    0.72
    pic
    0.70
    ql
    0.70
    Act Density 0.416%

    No Known Activations