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

    Neuronpedia

    INDEX
    Explanations

    words related to specific entities or brands

    oai_token-act-pair · gpt-3.5-turbo

    consonant sounds in specific words and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ingred
    -0.66
    xus
    -0.66
    REL
    -0.63
     kittens
    -0.60
    uties
    -0.58
    caps
    -0.57
    elight
    -0.56
    Ingredients
    -0.56
    hett
    -0.55
     srfAttach
    -0.55
    POSITIVE LOGITS
    vironment
    0.83
    ilon
    0.80
    tainment
    0.78
    anasia
    0.78
    hower
    0.77
    Reloaded
    0.75
     coli
    0.74
    ionage
    0.72
    911
    0.70
    iquette
    0.69
    Act Density 0.092%

    No Known Activations