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

    Neuronpedia

    INDEX
    Explanations

    words related to clothing items, specifically focusing on collars

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of collars in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulsion
    -0.76
     Centauri
    -0.74
    endi
    -0.73
     slideshow
    -0.70
    isoft
    -0.68
    lihood
    -0.68
     Archdemon
    -0.67
    aqu
    -0.64
    ORTS
    -0.63
     shalt
    -0.63
    POSITIVE LOGITS
    bones
    1.50
    bone
    1.40
    collar
    1.09
     collar
    0.92
     bone
    0.87
    oidal
    0.74
    tie
    0.73
     wool
    0.71
    bons
    0.70
    workers
    0.70
    Act Density 0.027%

    No Known Activations