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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restraint or holding back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jar
    -0.17
     Jar
    -0.16
    esses
    -0.16
     jar
    -0.15
     jars
    -0.15
     Lama
    -0.15
    jev
    -0.15
    ruh
    -0.14
     FLAGS
    -0.14
    Jar
    -0.14
    POSITIVE LOGITS
    Tac
    0.19
     until
    0.17
    illac
    0.15
     Until
    0.14
     Tac
    0.14
     tac
    0.14
     hasta
    0.14
    ÄĽtÅ¡
    0.14
    Until
    0.14
     sidelines
    0.14
    Act Density 0.219%

    No Known Activations