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

    Neuronpedia

    INDEX
    Explanations

    proper names related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or organization, likely related to journalism or reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.79
    aceae
    -0.75
    tions
    -0.67
    etts
    -0.66
    ocket
    -0.66
    ··
    -0.65
    gling
    -0.64
    atics
    -0.64
    OUP
    -0.64
    lda
    -0.64
    POSITIVE LOGITS
     ideological
    0.65
     blogs
    0.64
    cloneembedreportprint
    0.63
    creator
    0.62
     intellectual
    0.61
     Blog
    0.61
     cryptographic
    0.60
     contributed
    0.60
     vegan
    0.60
     Plaintiff
    0.58
    Act Density 0.221%

    No Known Activations