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

    Neuronpedia

    INDEX
    Explanations

    themes related to social commentary and responses to injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arend
    -0.16
     اÙĦØŃÙĬ
    -0.15
    inkel
    -0.15
    arna
    -0.15
     Fallon
    -0.14
    ocl
    -0.14
    forth
    -0.14
    achten
    -0.14
    ibo
    -0.14
    AZY
    -0.14
    POSITIVE LOGITS
     beams
    0.14
    ivec
    0.14
    lient
    0.14
     shells
    0.14
     ly
    0.14
     Lid
    0.14
    IVATE
    0.13
    .Unicode
    0.13
    AIT
    0.13
    OND
    0.13
    Act Density 0.527%

    No Known Activations