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

    Neuronpedia

    INDEX
    Explanations

    words related to independence or acting separately from others

    oai_token-act-pair · gpt-3.5-turbo

    instances of independence in actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tro
    -0.72
    ening
    -0.69
     mourning
    -0.64
    pell
    -0.63
     scar
    -0.62
    ema
    -0.61
    bus
    -0.59
    zing
    -0.59
    pex
    -0.58
    ubes
    -0.57
    POSITIVE LOGITS
     independently
    3.80
     separately
    1.67
     independent
    1.42
     individually
    1.42
    independent
    1.38
     jointly
    1.37
     autonom
    1.37
     independ
    1.30
     anonymously
    1.26
     concurrently
    1.24
    Act Density 0.010%

    No Known Activations