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

    Neuronpedia

    INDEX
    Explanations

    expressions of collective identity and solidarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustom
    -0.15
    anson
    -0.15
    _probe
    -0.14
    exampleInput
    -0.13
     سخ
    -0.13
    éĬ
    -0.13
    δÏģο
    -0.13
    iterals
    -0.13
    strom
    -0.13
     å½
    -0.13
    POSITIVE LOGITS
    Łèĥ½
    0.16
    Äĩ
    0.15
    lä
    0.15
    TTY
    0.15
    ILLISE
    0.15
    abwe
    0.14
     Conway
    0.14
    nth
    0.14
    ascade
    0.14
    ãĥ«ãĤ¯
    0.14
    Act Density 0.122%

    No Known Activations