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

    Neuronpedia

    INDEX
    Explanations

    words related to strained or tense situations or relationships

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to relationships and their stress or strain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropy
    -0.79
    raviolet
    -0.75
    gypt
    -0.75
     carriers
    -0.72
    eatures
    -0.72
    ing
    -0.71
    jriwal
    -0.71
    boarding
    -0.69
    tarians
    -0.69
    pillar
    -0.69
    POSITIVE LOGITS
    enegger
    0.93
    orio
    0.91
    NES
    0.82
    NRS
    0.82
    ptives
    0.80
    âĸijâĸij
    0.79
     Gin
    0.78
    ãģ®éŃĶ
    0.76
    oca
    0.76
    HTTP
    0.76
    Act Density 0.024%

    No Known Activations