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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong recommendation or positive assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aveug
    -0.50
    enumi
    -0.40
    
    -0.40
    ſelf
    -0.40
     bø
    -0.39
    Spacer
    -0.39
     malos
    -0.39
     buoni
    -0.39
    EndInit
    -0.39
    Console
    -0.39
    POSITIVE LOGITS
     highly
    0.56
     anticipated
    0.54
     Highly
    0.52
    Highly
    0.47
     coveted
    0.46
     contested
    0.45
     sought
    0.44
     desired
    0.44
     recommend
    0.44
    arschijnlijk
    0.44
    Act Density 0.128%

    No Known Activations