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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contextually significant linking words in descriptions of plots or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    478
    -0.16
     LU
    -0.15
    ihu
    -0.15
    бол
    -0.15
    olas
    -0.15
    ieg
    -0.14
     Ùħشار
    -0.14
    USH
    -0.14
    ards
    -0.14
    áli
    -0.14
    POSITIVE LOGITS
     Doom
    0.27
     Titans
    0.25
     Cy
    0.24
     Robot
    0.22
    Robot
    0.21
    Cy
    0.21
    Tit
    0.20
     Robin
    0.20
     DC
    0.20
     Beast
    0.20
    Act Density 0.001%

    No Known Activations