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

    Neuronpedia

    INDEX
    Explanations

    instances of loss or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _dc
    -0.15
    ober
    -0.14
    eer
    -0.14
    .Slf
    -0.14
     Klo
    -0.14
     Folk
    -0.14
    ragon
    -0.14
    icros
    -0.14
     lod
    -0.14
     gauche
    -0.14
    POSITIVE LOGITS
    combe
    0.19
    enthal
    0.17
    ffe
    0.16
    æİī
    0.15
     cap
    0.14
    _losses
    0.14
    :Object
    0.14
    Loss
    0.14
    ãi
    0.14
    CVE
    0.14
    Act Density 0.101%

    No Known Activations