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

    Neuronpedia

    INDEX
    Explanations

    discussions around accountability and hypocrisy in societal and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allenge
    -0.17
    .ARR
    -0.15
    roupon
    -0.14
    amma
    -0.14
    oser
    -0.14
    ocz
    -0.14
    é¡
    -0.14
    ETY
    -0.14
    SPELL
    -0.14
    .shutdown
    -0.14
    POSITIVE LOGITS
     talk
    0.34
    talk
    0.26
     claims
    0.26
    -talk
    0.26
     CLAIM
    0.25
     rhetoric
    0.24
     claimed
    0.24
     Talk
    0.24
    Talk
    0.24
     claim
    0.24
    Act Density 0.371%

    No Known Activations