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

    Neuronpedia

    INDEX
    Explanations

    references to a specific organization related to freedom

    oai_token-act-pair · gpt-3.5-turbo

    references to "Freedom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMS
    -0.71
    aco
    -0.69
    ENTS
    -0.69
    nas
    -0.68
    liam
    -0.67
     Kard
    -0.65
    ept
    -0.64
    illac
    -0.64
    eor
    -0.63
    amac
    -0.63
    POSITIVE LOGITS
     Fighters
    0.81
     prisoner
    0.77
     roam
    0.76
    Freedom
    0.76
     freedom
    0.75
     Freedom
    0.75
     Rights
    0.75
     Liberties
    0.74
    freedom
    0.73
    bies
    0.72
    Act Density 0.013%

    No Known Activations