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

    Neuronpedia

    INDEX
    Explanations

    words related to processing or manipulation of materials or resources

    oai_token-act-pair · gpt-3.5-turbo

    words associated with extraction and processing of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neigh
    -0.65
     subclass
    -0.64
     lawy
    -0.63
     nort
    -0.59
     Whe
    -0.58
     precedence
    -0.58
     Nig
    -0.58
    perty
    -0.58
     Supreme
    -0.58
     Racial
    -0.57
    POSITIVE LOGITS
    ment
    1.33
    able
    1.28
    ments
    1.25
    ables
    1.23
    ing
    1.14
    ability
    1.10
    ings
    1.04
    ation
    1.03
    MENT
    0.98
    ABLE
    0.98
    Act Density 0.233%

    No Known Activations