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

    Neuronpedia

    INDEX
    Explanations

    names of newspapers and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    098
    -0.17
    vek
    -0.15
    ignon
    -0.15
    keh
    -0.15
    097
    -0.15
    445
    -0.15
    lys
    -0.14
    umar
    -0.14
    107
    -0.14
     rec
    -0.14
    POSITIVE LOGITS
    /Dk
    0.19
    ousel
    0.18
    ÃĹ↵↵
    0.17
    ãĥĭãĥ¼
    0.17
    argout
    0.16
     outlet
    0.16
     exclusively
    0.16
    .scalablytyped
    0.15
     interviewer
    0.15
    odo
    0.14
    Act Density 0.027%

    No Known Activations