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

    Neuronpedia

    INDEX
    Explanations

    contextual references to situations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ///</
    -0.41
    AutoScaleMode
    -0.41
    DebuggerStep
    -0.40
     referenties
    -0.40
    Connection
    -0.38
    Autoritní
    -0.38
    
    -0.37
    protoimpl
    -0.36
     connessione
    -0.36
     localVar
    -0.35
    POSITIVE LOGITS
     hopes
    0.61
     onPostExecute
    0.60
    case
    0.56
    cognito
    0.54
     Vegas
    0.54
    consider
    0.52
    between
    0.51
     front
    0.51
    tim
    0.50
     hindsight
    0.49
    Act Density 0.472%

    No Known Activations