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

    Neuronpedia

    INDEX
    Explanations

    instances of contractions or possessives in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afil
    -0.18
    å£°éŁ³
    -0.14
    ëı
    -0.14
    mv
    -0.14
    ãĤĩ
    -0.14
    mx
    -0.14
    ormsg
    -0.14
    SWG
    -0.14
    人åĵ¡
    -0.13
    redient
    -0.13
    POSITIVE LOGITS
    if
    0.16
    LOPT
    0.15
    art
    0.15
    ataka
    0.15
    werk
    0.14
     most
    0.14
    .navigation
    0.14
    rib
    0.14
    alling
    0.14
    unkt
    0.14
    Act Density 0.033%

    No Known Activations