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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases that indicate personal or communal experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]`
    -0.42
    $",
    -0.38
    )”
    -0.36
    "]:
    -0.35
    ]."
    -0.35
    ]"
    -0.35
     Италијани
    -0.35
    .’’
    -0.35
    )":
    -0.34
    "];
    -0.34
    POSITIVE LOGITS
    IsContent
    0.71
    LabelTagHelper
    0.62
     meille
    0.56
    Datuak
    0.55
    TagHelper
    0.54
    makeText
    0.52
     tutkim
    0.50
    contentValues
    0.50
    !*\
    0.50
    twimg
    0.50
    Act Density 0.159%

    No Known Activations