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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and calculations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.60
     ComVisible
    -0.58
     NUKAT
    -0.58
     يتيمه
    -0.57
     sapore
    -0.55
    udia
    -0.53
     adanya
    -0.51
     numerosi
    -0.50
    znamu
    -0.50
     confronti
    -0.49
    POSITIVE LOGITS
     estimate
    0.81
     estimated
    0.81
     measured
    0.74
     estimation
    0.70
     estimates
    0.69
     Estimate
    0.68
     approximate
    0.67
     estimations
    0.67
     calcu
    0.65
     estim
    0.64
    Act Density 2.807%

    No Known Activations