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

    Neuronpedia

    INDEX
    Explanations

    words related to cooperation and shared goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suppress
    -0.16
    trs
    -0.15
    aria
    -0.15
    ienne
    -0.15
    LOY
    -0.15
    ead
    -0.15
    ivery
    -0.15
    abad
    -0.14
    abb
    -0.14
    ród
    -0.14
    POSITIVE LOGITS
     being
    0.31
     getting
    0.23
     having
    0.22
    being
    0.21
     making
    0.20
     becoming
    0.20
     doing
    0.19
    ÏİνÏĦαÏĤ
    0.19
     Being
    0.18
     correl
    0.18
    Act Density 0.435%

    No Known Activations