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

    Neuronpedia

    INDEX
    Explanations

    political or controversial terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to possessive forms and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.88
     mathemat
    -0.78
     optimizations
    -0.73
     princ
    -0.72
     regul
    -0.71
     carbohyd
    -0.70
     pharmacy
    -0.69
     unborn
    -0.68
     pyramid
    -0.68
     fortun
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.05
    İ
    0.85
    ï¸
    0.81
    cffffcc
    0.76
    TPS
    0.76
    PF
    0.75
    VICE
    0.74
    fter
    0.72
    SHA
    0.72
    HQ
    0.71
    Act Density 0.328%

    No Known Activations