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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a request for additional information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æīįèĥ½
    -0.15
    uzzi
    -0.14
    uir
    -0.14
    ãģŁãĤģãģ®
    -0.14
    vat
    -0.13
    ndata
    -0.13
    aklı
    -0.13
    uce
    -0.13
    xdb
    -0.13
    _uc
    -0.13
    POSITIVE LOGITS
     information
    0.30
     info
    0.24
    information
    0.24
     informatie
    0.23
     Information
    0.22
    ä¿¡æģ¯
    0.22
     información
    0.20
    _information
    0.20
    -information
    0.20
     details
    0.18
    Act Density 0.020%

    No Known Activations