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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their usage in emotional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ær
    -0.15
    γκα
    -0.14
    ught
    -0.14
    ement
    -0.14
    uters
    -0.14
    cent
    -0.14
    :\/\/
    -0.14
    ple
    -0.14
    etc
    -0.13
    ://'
    -0.13
    POSITIVE LOGITS
    ãĥ£
    0.16
    atak
    0.15
    ADO
    0.15
     mos
    0.14
    Ä±ÅŁÄ±k
    0.14
    lamaz
    0.14
    kul
    0.14
     fine
    0.14
     Král
    0.14
    454
    0.13
    Act Density 0.414%

    No Known Activations