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

    Neuronpedia

    INDEX
    Explanations

    words related to taking action or making a strong statement

    oai_token-act-pair · gpt-3.5-turbo

    words and forms associated with the concept of "ending" or "defending."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nostalgic
    -0.69
    bin
    -0.66
     stock
    -0.64
     stocking
    -0.63
     cust
    -0.63
     capable
    -0.62
     ripe
    -0.62
     collectively
    -0.60
     classrooms
    -0.60
    volume
    -0.60
    POSITIVE LOGITS
     Abuse
    0.82
     Response
    0.78
     Integrity
    0.76
     Defenders
    0.75
     Appeal
    0.75
     Fighters
    0.75
    ILA
    0.74
     Legislation
    0.74
    EMENT
    0.72
     Crit
    0.72
    Act Density 0.110%

    No Known Activations