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

    Neuronpedia

    INDEX
    Explanations

    references to censorship and the implications of free speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stim
    -0.15
    CRM
    -0.15
     abandonment
    -0.14
    ÑĢÑİ
    -0.14
    859
    -0.14
    778
    -0.14
    resizing
    -0.14
    Disposition
    -0.13
    abyrin
    -0.13
    uyết
    -0.13
    POSITIVE LOGITS
     censor
    0.52
     censorship
    0.51
     c
    0.35
    ensor
    0.34
    ensored
    0.33
     ÑĨ
    0.28
    Âłc
    0.27
     blocked
    0.27
     bans
    0.26
    ban
    0.25
    Act Density 0.169%

    No Known Activations