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

    Neuronpedia

    INDEX
    Explanations

    relations involving social dynamics and transformations in status or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flink
    -0.73
    basicConfig
    -0.64
    ntä
    -0.59
    WillAppear
    -0.59
     hangover
    -0.56
    RequestMapping
    -0.56
    |[]
    -0.55
     fortfarande
    -0.55
     ankara
    -0.54
     sexes
    -0.54
    POSITIVE LOGITS
     becomes
    0.90
     become
    0.88
     became
    0.86
    become
    0.82
    becomes
    0.78
     Become
    0.77
     Becomes
    0.76
    Become
    0.76
    fjspx
    0.75
    became
    0.72
    Act Density 0.525%

    No Known Activations