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

    Neuronpedia

    INDEX
    Explanations

    instances where support is expressed towards a particular person or cause

    oai_token-act-pair · gpt-3.5-turbo

    references to political endorsements or backing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shant
    -0.77
     earthqu
    -0.68
    oufl
    -0.67
     pores
    -0.66
    ¯¯
    -0.65
    ModLoader
    -0.63
     Hole
    -0.62
    juries
    -0.61
    bum
    -0.61
     Goddard
    -0.61
    POSITIVE LOGITS
    votes
    0.93
    itism
    0.89
    Support
    0.88
    enance
    0.81
    vote
    0.81
     endorse
    0.81
    byn
    0.80
     endorsing
    0.80
    Supporters
    0.77
     supporters
    0.77
    Act Density 0.057%

    No Known Activations