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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to authority and evidence in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cts
    -0.16
     pie
    -0.15
    WithData
    -0.15
    å©
    -0.15
     agency
    -0.14
    edula
    -0.14
    DOUBLE
    -0.14
    mediate
    -0.14
    elyn
    -0.14
     hal
    -0.14
    POSITIVE LOGITS
    ourke
    0.17
    >\<^
    0.15
    ouch
    0.15
    åģı
    0.14
    ILLE
    0.14
     Silk
    0.14
    êt
    0.14
    erset
    0.14
    orks
    0.14
    akers
    0.14
    Act Density 0.005%

    No Known Activations