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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "called in to"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readable
    -0.69
     reprinted
    -0.65
    xual
    -0.65
    TION
    -0.64
    ï¸
    -0.64
    pointers
    -0.61
    rag
    -0.61
     spawned
    -0.60
     uploaded
    -0.59
     priceless
    -0.59
    POSITIVE LOGITS
     camp
    0.80
     orbit
    0.80
    ondon
    0.78
     shore
    0.76
     defend
    0.76
     testify
    0.76
     celebrate
    0.74
    ichita
    0.72
     inspect
    0.71
     participate
    0.70
    Act Density 0.217%

    No Known Activations