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

    Neuronpedia

    INDEX
    Explanations

    instances of collective or group-related language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _OW
    -0.17
    isd
    -0.16
    pty
    -0.15
    оÑĤÑĮ
    -0.14
    arken
    -0.14
     treff
    -0.14
    parallel
    -0.14
    zers
    -0.14
    inis
    -0.14
    asurer
    -0.14
    POSITIVE LOGITS
     alike
    0.18
     their
    0.17
     tall
    0.16
     themselves
    0.15
     family
    0.15
    their
    0.15
     erst
    0.15
     Tall
    0.15
     loved
    0.14
     families
    0.14
    Act Density 0.133%

    No Known Activations