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

    Neuronpedia

    INDEX
    Explanations

    discussions related to political decisions and policies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .","
    -0.89
     [|
    -0.68
    .</
    -0.64
    peg
    -0.62
     ..."
    -0.61
     rot
    -0.60
    .''
    -0.60
     ______
    -0.60
     guiActiveUnfocused
    -0.60
    .""
    -0.60
    POSITIVE LOGITS
     irony
    0.66
     Feinstein
    0.65
     Cohn
    0.63
    iannopoulos
    0.63
     GOODMAN
    0.62
     Chomsky
    0.60
    partisan
    0.60
     Wasserman
    0.58
     Yiannopoulos
    0.58
     Corker
    0.57
    Act Density 1.766%

    No Known Activations