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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaiter
    -0.66
    ="@+
    -0.62
     quæ
    -0.61
     medesimo
    -0.60
     !_
    -0.60
     {},
    -0.59
     stället
    -0.59
     polvere
    -0.58
     sibi
    -0.56
    ///</
    -0.56
    POSITIVE LOGITS
     kinda
    0.60
     somewhere
    0.59
     outta
    0.57
     right
    0.53
     nuts
    0.52
     nicely
    0.52
     real
    0.51
    GeneratedMessage
    0.50
     though
    0.49
     threw
    0.48
    Act Density 0.155%

    No Known Activations