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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "together" and related forms indicating unity or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.85
    ]")]
    -0.83
     AssemblyTitle
    -0.78
    abstractmethod
    -0.76
    Rüyada
    -0.73
    ()]
    -0.73
     незавершена
    -0.73
    })*/
    -0.71
    LEncoder
    -0.70
    featureID
    -0.70
    POSITIVE LOGITS
    ness
    0.84
     TOGETHER
    0.61
     Together
    0.57
     together
    0.52
    together
    0.52
     взя
    0.51
    NESS
    0.50
     compacto
    0.48
    Together
    0.47
    antum
    0.47
    Act Density 0.073%

    No Known Activations