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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate economic or developmental goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¤ãģij
    -0.22
    è¦ĭ
    -0.19
    ãģ¤
    -0.17
    éĸĭ
    -0.16
     to
    -0.15
    to
    -0.15
    cq
    -0.14
    unj
    -0.14
    á»ħ
    -0.14
    cult
    -0.14
    POSITIVE LOGITS
    /from
    0.38
    gether
    0.36
    asting
    0.27
    plevel
    0.25
    asts
    0.25
     be
    0.24
    ying
    0.24
    ffee
    0.22
    iling
    0.21
    -date
    0.21
    Act Density 1.777%

    No Known Activations