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

    Neuronpedia

    INDEX
    Explanations

    words related to reporting or news coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arten
    -0.16
     McCart
    -0.15
     Tro
    -0.15
    ãĥĶ
    -0.14
    ipel
    -0.14
     tro
    -0.14
    bounding
    -0.14
    Tro
    -0.13
    tridge
    -0.13
    ughter
    -0.13
    POSITIVE LOGITS
    abol
    0.15
    ALA
    0.14
    iled
    0.14
    .Unity
    0.14
     weekly
    0.14
    ân
    0.14
    inoa
    0.14
    utow
    0.14
    sett
    0.14
    482
    0.14
    Act Density 0.060%

    No Known Activations