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

    Neuronpedia

    INDEX
    Explanations

    terms related to degeneration and degradation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eru
    -0.19
    ifax
    -0.16
    ÏįÏĢ
    -0.16
    vely
    -0.16
    ç«ĭãģ¦
    -0.15
    ytic
    -0.15
    er
    -0.15
    zsche
    -0.15
    ioneer
    -0.15
    iones
    -0.14
    POSITIVE LOGITS
    enerate
    0.29
     deg
    0.27
     Deg
    0.25
    enerative
    0.25
    Deg
    0.22
    enerated
    0.21
    eneration
    0.20
    ener
    0.20
     degradation
    0.19
    -rad
    0.19
    Act Density 0.007%

    No Known Activations