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

    Neuronpedia

    INDEX
    Explanations

    issues that are of importance or concern

    oai_token-act-pair · gpt-3.5-turbo

    references to various important societal or political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.88
    urses
    -0.84
    ellow
    -0.78
    ãĤ¨ãĥ«
    -0.76
    asty
    -0.75
    rontal
    -0.75
    forestation
    -0.74
    berman
    -0.74
    tsky
    -0.73
    ove
    -0.72
    POSITIVE LOGITS
     relating
    0.90
     plag
    0.88
     arising
    0.86
     affecting
    0.86
    etter
    0.84
     pertaining
    0.84
     stemming
    0.83
    afety
    0.82
    manship
    0.81
    hooting
    0.79
    Act Density 0.033%

    No Known Activations