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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and positive feelings towards collaboration and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.68
     resourceCulture
    -0.61
    aarrggbb
    -0.48
    écnicas
    -0.47
     EconPapers
    -0.46
     clerks
    -0.46
     consciousness
    -0.46
    StoryboardSegue
    -0.46
     Spri
    -0.45
     teeth
    -0.44
    POSITIVE LOGITS
    contentLoaded
    0.66
     Complement
    0.60
    Esperamos
    0.57
    illir
    0.56
     delighted
    0.55
     remercier
    0.54
    Personendaten
    0.54
     freuen
    0.54
     complement
    0.54
     soulign
    0.53
    Act Density 0.100%

    No Known Activations