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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positioning or establishment in a firm or secure manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strong stability or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emin
    -0.86
    vernment
    -0.76
    externalActionCode
    -0.75
    olan
    -0.75
    nesota
    -0.74
    ebin
    -0.73
     tables
    -0.73
    OTOS
    -0.72
    igraph
    -0.72
     Plans
    -0.66
    POSITIVE LOGITS
     entrenched
    0.88
     planted
    0.88
     rooted
    0.87
     cement
    0.85
    ãĤ©
    0.84
     ens
    0.81
     anchored
    0.80
    lishes
    0.79
     ingrained
    0.78
     etched
    0.78
    Act Density 0.010%

    No Known Activations