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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to identity and labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.62
     Roskov
    -0.62
    TypedDataSet
    -0.58
     BrowserModule
    -0.56
    \{\\
    -0.55
     témoig
    -0.55
     Италијани
    -0.52
    pexpr
    -0.52
    RTLR
    -0.50
     preſent
    -0.50
    POSITIVE LOGITS
     coined
    0.84
     connotations
    0.81
     referring
    0.75
     denoting
    0.71
     synonymous
    0.69
     used
    0.67
     derived
    0.66
     descriptive
    0.64
     connotation
    0.64
     evocative
    0.63
    Act Density 0.471%

    No Known Activations