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

    Neuronpedia

    INDEX
    Explanations

    words related to being deeply connected or having a strong foundation in something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of being "rooted in" various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    named
    -0.89
    NOW
    -0.75
    itle
    -0.71
     tempted
    -0.71
    label
    -0.70
    killed
    -0.68
    isan
    -0.68
    vous
    -0.67
    casters
    -0.67
    ŀ
    -0.66
    POSITIVE LOGITS
    escap
    1.11
     lieu
    1.06
    effic
    1.05
     spite
    1.03
     accordance
    1.03
     obscurity
    0.92
     vitro
    0.92
     anticipation
    0.92
     academia
    0.88
    authent
    0.86
    Act Density 0.181%

    No Known Activations