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

    Neuronpedia

    INDEX
    Explanations

    references to user awareness and privacy practices related to content and other sites

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.73
    InjectAttribute
    -0.73
    UVWXYZ
    -0.67
    ujesz
    -0.61
    ernalia
    -0.60
    UnsafeEnabled
    -0.59
    mű
    -0.59
    ientí
    -0.56
    Życiorys
    -0.56
     Runway
    -0.56
    POSITIVE LOGITS
     peccato
    0.46
    CodedInputStream
    0.44
    сылкі
    0.44
     başına
    0.44
     estratég
    0.43
    大部分
    0.43
    aarrggbb
    0.43
    ofte
    0.43
    paksa
    0.43
     usaha
    0.42
    Act Density 0.028%

    No Known Activations