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

    Neuronpedia

    INDEX
    Explanations

    titles of movies and songs

    oai_token-act-pair · gpt-3.5-turbo

    titles and names of films, songs, or works of art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hosp
    -0.68
     contempor
    -0.68
    ipel
    -0.64
    major
    -0.63
     photoc
    -0.63
    hair
    -0.62
     DIRECT
    -0.58
     chem
    -0.58
     CONTR
    -0.57
     scram
    -0.56
    POSITIVE LOGITS
    Ħ¢
    0.86
     Thrones
    0.85
     Awakening
    0.79
     Lumpur
    0.78
     Awakens
    0.76
     Remix
    0.75
    Ń·
    0.70
     Freak
    0.70
     Jinn
    0.70
    chu
    0.69
    Act Density 0.264%

    No Known Activations