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

    Neuronpedia

    INDEX
    Explanations

    hashtags on social media

    oai_token-act-pair · gpt-3.5-turbo

    references to hashtags and trending topics on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.81
    undai
    -0.80
    odcast
    -0.72
     oun
    -0.68
    artment
    -0.68
    ramid
    -0.68
     destro
    -0.68
    ateral
    -0.68
     tremend
    -0.67
    llah
    -0.66
    POSITIVE LOGITS
     hashtag
    1.25
     hasht
    1.09
    tags
    1.08
    ="#
    1.00
     "#
    0.98
    =""
    0.90
    âĢİ
    0.84
     (#
    0.79
    =\"
    0.77
    saf
    0.77
    Act Density 0.007%

    No Known Activations