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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals are being sent somewhere

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.67
     composure
    -0.60
    profit
    -0.60
     concession
    -0.59
    kernel
    -0.58
     advoc
    -0.56
    foundation
    -0.56
     eater
    -0.55
    Enough
    -0.55
     possibilities
    -0.55
    POSITIVE LOGITS
    inel
    1.31
    enced
    1.03
    entious
    1.02
     abroad
    0.92
    irection
    0.87
    imental
    0.85
    encing
    0.81
    encer
    0.80
    opolis
    0.80
    pez
    0.76
    Act Density 0.043%

    No Known Activations