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

    Neuronpedia

    INDEX
    Explanations

    instances of apologies and expressions of remorse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    men
    -0.15
     la
    -0.15
    lige
    -0.15
    ıma
    -0.15
    lake
    -0.14
    /types
    -0.14
    ãĥ¼ãĤ¹
    -0.14
    ãģĵãĤį
    -0.14
    632
    -0.14
    iston
    -0.14
    POSITIVE LOGITS
    ylon
    0.17
    ÑģоÑĢ
    0.15
    apor
    0.14
    .Factory
    0.14
    stell
    0.14
    archy
    0.14
    uger
    0.14
    oval
    0.14
     prostituer
    0.14
    nothing
    0.13
    Act Density 0.020%

    No Known Activations