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

    Neuronpedia

    INDEX
    Explanations

    discussions about professional topics and projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.93
    évaluateur
    -0.84
    DebuggerNonUser
    -0.75
     Grecs
    -0.72
    InitVars
    -0.69
    Personendaten
    -0.65
    AntiForgeryToken
    -0.64
     ruota
    -0.62
     uș
    -0.62
    ForValue
    -0.61
    POSITIVE LOGITS
    ousse
    0.53
    atschappij
    0.52
     indeed
    0.52
     referrerpolicy
    0.50
     wonderful
    0.48
    anker
    0.48
    ratulations
    0.48
     Indeed
    0.48
    unggulan
    0.47
    havior
    0.46
    Act Density 0.740%

    No Known Activations