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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assertion or persuasion

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     litter
    -0.56
    FB
    -0.55
    AMD
    -0.54
    weed
    -0.53
    Site
    -0.52
     --
    -0.51
     Rhino
    -0.51
    tags
    -0.51
     rest
    -0.50
    HP
    -0.50
    POSITIVE LOGITS
    selves
    0.92
    etheless
    0.90
    areth
    0.78
    lynn
    0.74
    ociation
    0.74
    este
    0.73
    olution
    0.71
    fw
    0.71
    acters
    0.69
    uddenly
    0.69
    Act Density 0.246%

    No Known Activations