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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning causality and factors affecting outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Turing
    -0.15
    á»Ļp
    -0.15
    anke
    -0.15
    chai
    -0.15
     removeObject
    -0.15
    ocard
    -0.14
    /fw
    -0.14
    âĢŀP
    -0.14
    åĭĩ
    -0.14
    edl
    -0.14
    POSITIVE LOGITS
    818
    0.15
    isans
    0.15
    ibur
    0.14
    eland
    0.14
    å¶
    0.14
     co
    0.14
     createContext
    0.13
    ipp
    0.13
     why
    0.13
     darkness
    0.13
    Act Density 0.011%

    No Known Activations