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

    Neuronpedia

    INDEX
    Explanations

    references to political issues and calls for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eventuell
    -0.55
     supuestamente
    -0.54
     Possibly
    -0.50
     allegedly
    -0.50
     theoretically
    -0.50
     Theore
    -0.49
     evtl
    -0.49
     supposedly
    -0.49
     Apparently
    -0.48
    Possibly
    -0.47
    POSITIVE LOGITS
     protections
    0.59
     bugün
    0.53
     hardworking
    0.53
     memastikan
    0.53
     rightly
    0.52
     noastre
    0.52
     dobbiamo
    0.52
     underscores
    0.52
     essenziale
    0.51
     chiare
    0.51
    Act Density 0.475%

    No Known Activations