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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experiences or actions that have occurred

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĺħ
    -0.65
     vacc
    -0.63
    ilings
    -0.63
    mson
    -0.62
    arning
    -0.61
     currently
    -0.60
    Soc
    -0.60
    heter
    -0.59
     Currently
    -0.57
    ethy
    -0.57
    POSITIVE LOGITS
     dealings
    1.01
     trouble
    0.97
     difficulty
    0.96
     enough
    0.85
     difficulties
    0.83
     recourse
    0.82
     success
    0.81
     intercourse
    0.80
    iths
    0.80
     setbacks
    0.79
    Act Density 0.086%

    No Known Activations