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

    Neuronpedia

    INDEX
    Explanations

    themes related to freedom, individual choice, and personal autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.60
    cotta
    -0.57
    ContentAlignment
    -0.57
     miser
    -0.56
    makeText
    -0.55
    statechange
    -0.55
    tvguidetime
    -0.54
     cref
    -0.53
     homophobic
    -0.52
     ashamed
    -0.51
    POSITIVE LOGITS
     freedom
    1.25
    Freedom
    1.13
     Freedom
    1.10
    freedom
    1.09
     unrestricted
    1.02
     freely
    1.02
     freedoms
    1.00
     free
    0.99
     bebas
    0.99
     libre
    0.98
    Act Density 0.362%

    No Known Activations