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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mutual benefit and cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lio
    -0.15
    ÏĥÏĦά
    -0.15
    statistics
    -0.15
    aug
    -0.15
    gor
    -0.14
    <typeof
    -0.14
    ä¸Ģèµ·
    -0.14
    Ấ
    -0.14
    ầu
    -0.14
    idel
    -0.14
    POSITIVE LOGITS
     mutually
    0.22
     Mutual
    0.21
    istic
    0.21
     mutual
    0.20
    ities
    0.20
    mut
    0.17
     agreed
    0.16
     reciprocal
    0.16
     exclusive
    0.15
    Mut
    0.15
    Act Density 0.008%

    No Known Activations