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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to keeping things in order or maintaining certain standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of maintaining consistency and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haps
    -0.72
    leton
    -0.70
    lot
    -0.67
    asus
    -0.63
     Caption
    -0.62
    ALLY
    -0.62
     unfocusedRange
    -0.61
    bernatorial
    -0.61
     Rivals
    -0.61
     Shutterstock
    -0.61
    POSITIVE LOGITS
     afloat
    1.23
     alive
    1.11
     accountable
    1.00
     intact
    0.93
     manageable
    0.85
     entertained
    0.82
     wraps
    0.81
     unchanged
    0.79
     safe
    0.78
     quiet
    0.77
    Act Density 0.135%

    No Known Activations