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

    Neuronpedia

    INDEX
    Explanations

    phrases related to management or leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and visiting structures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.81
    hooting
    -0.75
    ega
    -0.74
    ses
    -0.73
    owship
    -0.72
    ooting
    -0.71
    iness
    -0.70
    oot
    -0.69
    aign
    -0.69
    eus
    -0.68
    POSITIVE LOGITS
    tons
    0.83
     engagements
    0.81
     conventions
    0.78
     platforms
    0.73
     mammals
    0.71
     agents
    0.71
     heights
    0.69
    AME
    0.69
     assignments
    0.68
    redients
    0.68
    Act Density 0.576%

    No Known Activations