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

    Neuronpedia

    INDEX
    Explanations

    key terms related to alignment and associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -1.02
     feroit
    -0.94
     AssemblyCulture
    -0.94
    :✨
    -0.93
     ExecuteAsync
    -0.91
     pouvoit
    -0.90
     auroit
    -0.88
     étoit
    -0.88
    Personendaten
    -0.88
    expandindo
    -0.87
    POSITIVE LOGITS
     also
    1.03
     همچنین
    0.81
     inoltre
    0.73
    also
    0.73
    Also
    0.71
     также
    0.69
     ALSO
    0.67
     Also
    0.67
     juga
    0.66
     furthermore
    0.64
    Act Density 0.176%

    No Known Activations