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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performing actions or making things happen, particularly in relation to improvement or achievement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "make" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.64
    stration
    -0.63
    rous
    -0.62
    ;;;;
    -0.61
     Mub
    -0.60
     Niet
    -0.59
     alluded
    -0.59
     presided
    -0.58
    ander
    -0.57
    hood
    -0.57
    POSITIVE LOGITS
     sure
    1.32
    hift
    1.04
     adjustments
    0.85
     sense
    0.81
    solete
    0.75
     AMERICA
    0.74
     repairs
    0.73
    URE
    0.73
     decisions
    0.72
     ends
    0.71
    Act Density 0.119%

    No Known Activations