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

    Neuronpedia

    INDEX
    Explanations

    words associated with creation and impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.15
    isan
    -0.15
    ÑĶм
    -0.15
    whelming
    -0.14
    geh
    -0.14
    essler
    -0.13
    ÄĽn
    -0.13
    #####↵
    -0.13
    xico
    -0.13
    aris
    -0.12
    POSITIVE LOGITS
     earlier
    0.17
     themselves
    0.17
    /generated
    0.15
    irectory
    0.15
     yesterday
    0.15
    rys
    0.15
    halb
    0.15
    leine
    0.14
    à¥įà¤Ĺत
    0.14
    Earlier
    0.14
    Act Density 0.448%

    No Known Activations