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

    Neuronpedia

    INDEX
    Explanations

    proposed solutions and workarounds for problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reuse
    -0.20
    rys
    -0.17
     Merchant
    -0.15
    reau
    -0.15
    UNC
    -0.15
     آش
    -0.15
    rette
    -0.14
    Merchant
    -0.14
    _phys
    -0.14
    roke
    -0.14
    POSITIVE LOGITS
    iken
    0.15
    gebra
    0.15
    ëijIJ
    0.13
    ORMAT
    0.13
    romise
    0.13
    -Origin
    0.13
    quine
    0.13
    ramid
    0.13
    inx
    0.13
     RELEASE
    0.13
    Act Density 0.108%

    No Known Activations