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

    Neuronpedia

    INDEX
    Explanations

    themes related to crime and deception in a dramatic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    709
    -0.16
     ÙĨبÙĪد
    -0.15
     Yesterday
    -0.15
    eos
    -0.14
    à¸Ħว
    -0.14
    Yesterday
    -0.14
     Yourself
    -0.13
    ãģĹãģ¾ãģĹãģŁ
    -0.13
     adress
    -0.13
    eydi
    -0.13
    POSITIVE LOGITS
     things
    0.30
    things
    0.24
    Things
    0.24
     Things
    0.24
     will
    0.23
     matters
    0.23
     events
    0.23
     soon
    0.21
     Enter
    0.21
     enter
    0.20
    Act Density 0.090%

    No Known Activations