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

    Neuronpedia

    INDEX
    Explanations

    political sponsors or co-sponsors mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to sponsorship and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Limbaugh
    -0.74
    theless
    -0.73
    lly
    -0.66
     Akin
    -0.65
    ity
    -0.63
     Sic
    -0.62
     snail
    -0.62
     snow
    -0.61
     pert
    -0.60
     Pav
    -0.60
    POSITIVE LOGITS
    ors
    2.63
    orship
    2.28
    ored
    2.28
    oring
    2.20
    or
    2.19
    ORS
    1.90
    ours
    1.75
    orable
    1.74
    oric
    1.73
    ORED
    1.71
    Act Density 0.118%

    No Known Activations