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

    Neuronpedia

    INDEX
    Explanations

    references to nature or the environment

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to physical structures and natural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tains
    -0.77
    soever
    -0.71
    Recomm
    -0.65
    PLA
    -0.61
    doms
    -0.60
    Recommend
    -0.60
    gery
    -0.59
     subjects
    -0.56
    nant
    -0.56
    Allows
    -0.56
    POSITIVE LOGITS
     were
    1.14
     are
    1.12
     weren
    1.11
     aren
    1.06
     remain
    0.99
     have
    0.96
     expire
    0.90
     revert
    0.90
    cape
    0.90
     collided
    0.89
    Act Density 0.247%

    No Known Activations