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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and names of creative works, particularly films or songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bley
    -0.72
     arsen
    -0.70
    nas
    -0.67
     thor
    -0.65
    psey
    -0.64
     offic
    -0.63
    ivable
    -0.63
    ã
    -0.63
    ishers
    -0.62
     "@
    -0.62
    POSITIVE LOGITS
     Remastered
    0.93
    ebted
    0.88
     Reloaded
    0.83
     Redux
    0.78
     Volume
    0.78
     Strikes
    0.77
     starring
    0.76
     anthology
    0.75
    feat
    0.74
     Remix
    0.74
    Act Density 0.470%

    No Known Activations