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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enstein
    -0.19
    icz
    -0.18
     Lucas
    -0.16
    emos
    -0.15
    оÑĢож
    -0.15
     Odd
    -0.14
    á»Ļi
    -0.14
    oothing
    -0.13
    ãģªãģĮãĤī
    -0.13
    467
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.17
    æĭĶ
    0.16
    ACHE
    0.15
    iled
    0.15
    ModelProperty
    0.14
    igkeit
    0.14
    ges
    0.14
    pper
    0.14
    akk
    0.13
    bole
    0.13
    Act Density 0.057%

    No Known Activations