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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating perception or evaluation of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectivement
    -0.57
     Act
    -0.53
     szív
    -0.52
     chiesto
    -0.52
    flashdata
    -0.51
    sprüng
    -0.51
     respectivos
    -0.51
     I
    -0.51
    hammad
    -0.50
    tetur
    -0.50
    POSITIVE LOGITS
     seem
    0.97
    enumi
    0.92
     seemed
    0.91
     seems
    0.90
     Parece
    0.89
    Seems
    0.87
    seems
    0.86
     scheint
    0.85
     actionMode
    0.84
     CreateTagHelper
    0.83
    Act Density 0.181%

    No Known Activations