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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies and societal concepts

    oai_token-act-pair · gpt-3.5-turbo

    statements related to societal issues and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.57
    ]).
    -0.55
    DCS
    -0.53
    "))
    -0.51
    ãĤ´ãĥ³
    -0.49
    collect
    -0.48
    jiang
    -0.48
    issance
    -0.48
    èĢ
    -0.46
     Beir
    -0.46
    POSITIVE LOGITS
     weaker
    0.46
     bounce
    0.46
     weak
    0.44
     however
    0.44
     horrible
    0.43
     machine
    0.42
     machines
    0.41
     knowing
    0.41
     sed
    0.40
     though
    0.40
    Act Density 4.031%

    No Known Activations