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

    Neuronpedia

    INDEX
    Explanations

    the concept of unity and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]")]
    -0.89
    voerd
    -0.77
     ARP
    -0.74
    fxml
    -0.74
    andExpect
    -0.74
    üf
    -0.74
     ExecuteAsync
    -0.73
     Sins
    -0.72
     Abp
    -0.69
    kano
    -0.68
    POSITIVE LOGITS
     Together
    0.97
     together
    0.94
    GETHER
    0.93
     TOGETHER
    0.92
    Together
    0.86
    together
    0.84
    ness
    0.72
    在一起
    0.68
    izer
    0.64
     juntas
    0.58
    Act Density 0.054%

    No Known Activations