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

    Neuronpedia

    INDEX
    Explanations

    instances of specific locational phrases and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instead
    -0.16
    agedList
    -0.14
    yh
    -0.14
     eldre
    -0.14
    ijk
    -0.14
    tti
    -0.14
     eventually
    -0.13
    term
    -0.13
     anv
    -0.13
     funny
    -0.13
    POSITIVE LOGITS
    ANTS
    0.23
    er
    0.22
    ants
    0.22
     le
    0.21
     les
    0.18
     cet
    0.18
     ce
    0.18
    antes
    0.17
    ante
    0.17
     pres
    0.17
    Act Density 0.009%

    No Known Activations