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

    Neuronpedia

    INDEX
    Explanations

    words related to personal experiences and engagement in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARTH
    -0.15
     Harris
    -0.15
    izen
    -0.14
    037
    -0.14
     Beam
    -0.14
    ibble
    -0.14
    ãģłãģ£ãģ¦
    -0.13
     à¤Ĩव
    -0.13
    ponge
    -0.13
     æĺŁ
    -0.13
    POSITIVE LOGITS
    ÙIJر
    0.16
     separ
    0.15
    abei
    0.15
    673
    0.14
    ساس
    0.14
    ông
    0.14
     numberWith
    0.14
    ovolta
    0.14
     Brooke
    0.14
    imum
    0.14
    Act Density 0.001%

    No Known Activations