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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the introduction or implementation of new technologies or products

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the release and production of media and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adv
    -0.66
    atin
    -0.60
     Surface
    -0.57
     panel
    -0.57
     distinguished
    -0.57
    mal
    -0.56
     ego
    -0.55
     Sunshine
    -0.53
     cop
    -0.52
    outer
    -0.52
    POSITIVE LOGITS
    éĹ
    0.92
     sooner
    0.88
     ASAP
    0.82
     tomorrow
    0.82
     prematurely
    0.82
     shortly
    0.76
    æ©
    0.74
     soon
    0.73
    âĢİ
    0.72
     anew
    0.70
    Act Density 0.245%

    No Known Activations