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

    Neuronpedia

    INDEX
    Explanations

    references to amateurs or amateur activities

    oai_token-act-pair · gpt-3.5-turbo

    references to amateurism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metics
    -0.72
    LOC
    -0.70
    reens
    -0.66
    ACTED
    -0.65
    appy
    -0.65
    dated
    -0.64
    lined
    -0.64
    uncture
    -0.63
    ahead
    -0.63
    eger
    -0.63
    POSITIVE LOGITS
    ishly
    1.04
    ish
    0.87
    ateur
    0.83
    ism
    0.79
     astronomer
    0.78
     boxing
    0.77
     scouting
    0.76
    ateurs
    0.74
     radio
    0.74
    onte
    0.73
    Act Density 0.028%

    No Known Activations