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

    Neuronpedia

    INDEX
    Explanations

    words related to personal characteristics and attributes

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and expressions of unity or connection among concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.94
    vier
    -0.82
    anche
    -0.77
    gap
    -0.75
    irection
    -0.75
    azard
    -0.72
    otropic
    -0.72
    auri
    -0.71
    hig
    -0.71
    rake
    -0.69
    POSITIVE LOGITS
     sensibilities
    0.94
     faculties
    0.87
     accomplishments
    0.86
     habits
    0.85
     namesake
    0.85
     selves
    0.83
     heritage
    0.80
     livelihood
    0.80
     counterparts
    0.79
     abilities
    0.78
    Act Density 0.543%

    No Known Activations