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

    Neuronpedia

    INDEX
    Explanations

    terms related to interactions and alignment in complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picchu
    -0.52
    enterOuterAlt
    -0.48
    httphttps
    -0.45
    YourGuide
    -0.43
    transQ
    -0.40
    érance
    -0.39
     CreateTagHelper
    -0.39
     intptr
    -0.39
    endphp
    -0.39
     GLASS
    -0.38
    POSITIVE LOGITS
     networking
    0.75
     social
    0.73
     socializing
    0.71
     socialization
    0.70
     communal
    0.69
    Networking
    0.68
     socialize
    0.68
    social
    0.68
     interpersonal
    0.67
    Social
    0.66
    Act Density 1.237%

    No Known Activations