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

    Neuronpedia

    INDEX
    Explanations

    phrases related to freedom or liberation

    oai_token-act-pair · gpt-3.5-turbo

    themes of freedom and liberation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
    batch
    -0.72
     Audit
    -0.71
    Solution
    -0.71
    Poké
    -0.70
    etimes
    -0.70
    yes
    -0.67
    YES
    -0.66
     Effective
    -0.66
    Sym
    -0.63
    POSITIVE LOGITS
     inhib
    1.04
     shack
    0.93
     reliance
    0.91
     burdens
    0.90
     dependence
    0.89
     precon
    0.88
     restraints
    0.85
     constraints
    0.84
     restrictive
    0.83
     fear
    0.82
    Act Density 0.225%

    No Known Activations