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

    Neuronpedia

    INDEX
    Explanations

    words related to communication, specifically involving telling or explaining something to others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of communication or assertions made by the speaker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idges
    -0.70
    eele
    -0.67
    metadata
    -0.67
    ONSORED
    -0.66
    scope
    -0.65
    ynski
    -0.64
    thinkable
    -0.62
    atus
    -0.62
    helps
    -0.62
    artifacts
    -0.60
    POSITIVE LOGITS
     myself
    1.86
     my
    1.20
     him
    1.18
     ourselves
    1.12
     them
    1.07
     everybody
    1.01
     anybody
    1.01
     somebody
    0.98
     everyone
    0.95
     THEM
    0.93
    Act Density 0.453%

    No Known Activations