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

    Neuronpedia

    INDEX
    Explanations

    phrases about news and journalism

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty or non-meaningful sections in the text, indicating a lack of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.74
     Seym
    -0.73
     Niet
    -0.67
    ãĥ¼ãĥĨ
    -0.67
     Chero
    -0.64
    å§
    -0.63
     fert
    -0.63
     Kurd
    -0.63
     destro
    -0.63
    accompan
    -0.62
    POSITIVE LOGITS
    lash
    0.81
    hi
    0.78
    rael
    0.76
    reet
    0.73
    utenberg
    0.71
    afe
    0.71
    ourge
    0.71
    hot
    0.69
    pace
    0.68
     Latest
    0.67
    Act Density 0.028%

    No Known Activations