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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal or global issues and progress

    oai_token-act-pair · gpt-3.5-turbo

    references to global and societal themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obos
    -0.82
    ĺ
    -0.75
    quished
    -0.75
    asts
    -0.71
    avier
    -0.70
    advertising
    -0.68
    apons
    -0.68
    oes
    -0.67
    effects
    -0.66
    ãĤ¨ãĥ«
    -0.66
    POSITIVE LOGITS
     nutshell
    1.01
     shenan
    0.73
     understatement
    0.70
     Canaver
    0.69
     pecul
    0.69
    gie
    0.65
     Beir
    0.64
    peak
    0.64
     Ic
    0.64
     ploy
    0.63
    Act Density 0.497%

    No Known Activations