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

    Neuronpedia

    INDEX
    Explanations

    words related to sports

    oai_token-act-pair · gpt-3.5-turbo

    sentences that represent definitive statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riet
    -0.77
     censored
    -0.76
     reprodu
    -0.74
     autonom
    -0.73
     compulsory
    -0.72
     oxy
    -0.71
    orno
    -0.70
    izoph
    -0.68
     censorship
    -0.67
     literature
    -0.67
    POSITIVE LOGITS
     Granted
    1.13
     Regardless
    1.03
     Rookie
    1.01
     Those
    1.01
     Obviously
    1.00
     Additionally
    0.98
     Athlet
    0.98
     Combine
    0.98
     Unfortunately
    0.97
     Still
    0.96
    Act Density 0.520%

    No Known Activations