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

    Neuronpedia

    INDEX
    Explanations

    elements related to physical interaction and emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ByDefault
    -0.53
    Bloomberg
    -0.50
    ình
    -0.49
    ųjų
    -0.47
    енча
    -0.47
    ponen
    -0.46
    ii
    -0.45
    HasColumnName
    -0.45
    nál
    -0.45
     besteht
    -0.45
    POSITIVE LOGITS
     wondering
    0.83
     unaware
    0.80
     hoping
    0.79
     wishing
    0.78
     unable
    0.77
     oblivious
    0.73
     unwilling
    0.71
     seeming
    0.71
     causing
    0.70
     knowing
    0.69
    Act Density 0.137%

    No Known Activations