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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "training" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hausen
    -0.17
     ëģ
    -0.16
    unto
    -0.16
    ahun
    -0.16
    èles
    -0.16
    .gdx
    -0.16
    -fw
    -0.15
    лаб
    -0.15
    ertz
    -0.15
    ernes
    -0.15
    POSITIVE LOGITS
    coil
    0.15
    ipur
    0.15
    æĿī
    0.14
    åıijåĩº
    0.14
     Poss
    0.14
     Sed
    0.14
    789
    0.13
    ı
    0.13
    ucid
    0.13
    ippy
    0.13
    Act Density 0.025%

    No Known Activations