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

    Neuronpedia

    INDEX
    Explanations

    names of characters or actors involved in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    709
    -0.16
    inde
    -0.15
    kola
    -0.14
    .dds
    -0.14
     à¤īसन
    -0.14
    allon
    -0.13
    shiv
    -0.13
    hte
    -0.13
    assi
    -0.13
     adress
    -0.13
    POSITIVE LOGITS
     will
    0.21
     Meanwhile
    0.19
     soon
    0.19
     meanwhile
    0.18
     things
    0.17
    will
    0.17
     Soon
    0.17
    things
    0.17
     unb
    0.16
     danger
    0.16
    Act Density 0.099%

    No Known Activations