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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantifiers related to losses and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ober
    -0.08
    .Slf
    -0.07
    eer
    -0.07
    aco
    -0.06
    aal
    -0.06
    ehr
    -0.06
     Gro
    -0.06
    νομα
    -0.06
    èİī
    -0.06
    iras
    -0.06
    POSITIVE LOGITS
     losses
    0.09
    æİī
    0.08
     loss
    0.08
    Loss
    0.07
     Lose
    0.07
    -loss
    0.07
     Loss
    0.07
    lose
    0.07
    combe
    0.07
     equ
    0.07
    Act Density 0.047%

    No Known Activations