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

    Neuronpedia

    INDEX
    Explanations

    instances where the concept of "being there" is emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "there"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FTA
    -0.64
     comprom
    -0.64
     CJ
    -0.61
     QUEST
    -0.60
     fibers
    -0.59
     Cum
    -0.58
     wounds
    -0.57
     lymph
    -0.56
    GET
    -0.56
    juries
    -0.56
    POSITIVE LOGITS
    abouts
    1.23
    tical
    0.89
    inel
    0.85
    itored
    0.81
    inar
    0.79
     Somewhere
    0.78
    ngth
    0.74
    upon
    0.71
    çĶŁ
    0.70
    arity
    0.69
    Act Density 0.044%

    No Known Activations