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

    Neuronpedia

    INDEX
    Explanations

    phrases related to containment or restriction

    oai_token-act-pair · gpt-3.5-turbo

    references to sustenance or maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profiling
    -0.62
     legislative
    -0.61
     wrapper
    -0.61
     collusion
    -0.60
     CES
    -0.60
     dozen
    -0.60
     ZIP
    -0.60
     curled
    -0.60
     present
    -0.59
     DUI
    -0.59
    POSITIVE LOGITS
    ains
    4.66
    ained
    2.47
    aining
    2.45
    ain
    2.38
    AIN
    2.02
    ainer
    1.71
    ainers
    1.39
    aine
    1.37
    aints
    1.31
    rain
    1.11
    Act Density 0.004%

    No Known Activations