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

    Neuronpedia

    INDEX
    Explanations

    words indicating causation or hypotheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.49
     незавершена
    -0.44
    tanleria
    -0.40
    JspWriter
    -0.40
    原始内容存档于
    -0.40
     Chwiliwch
    -0.38
     demas
    -0.37
    abspath
    -0.36
    RTDA
    -0.36
    Personensuche
    -0.36
    POSITIVE LOGITS
     decides
    0.48
     decided
    0.47
     därför
    0.44
     derfor
    0.44
    myModal
    0.44
     InputDecoration
    0.43
    batore
    0.42
    จึง
    0.42
     decide
    0.41
     beslu
    0.41
    Act Density 0.452%

    No Known Activations