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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with dramatic events and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģłãģĭãĤī
    -0.14
    utral
    -0.14
    981
    -0.13
    nowled
    -0.13
    oga
    -0.13
    china
    -0.13
    loy
    -0.13
    å¯
    -0.13
     èŤ
    -0.13
    -Compatible
    -0.12
    POSITIVE LOGITS
     courtesy
    0.22
     إذ
    0.21
     thanks
    0.19
     denn
    0.18
    :
    0.18
     καθÏİÏĤ
    0.17
    ãģĭãģ®
    0.17
     when
    0.16
     as
    0.16
     indeed
    0.15
    Act Density 0.374%

    No Known Activations