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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dependency or reliance on someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to reliance or dependence on others or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.67
    uesday
    -0.64
     NX
    -0.63
    IAS
    -0.61
     Topic
    -0.61
    achu
    -0.60
    ovember
    -0.59
    ãĥ¯ãĥ³
    -0.58
    DEM
    -0.58
    rosse
    -0.58
    POSITIVE LOGITS
     larg
    0.85
     alone
    0.84
     outweigh
    0.76
     for
    0.75
     sidelines
    0.73
     to
    0.73
     instincts
    0.71
     generosity
    0.71
     sparing
    0.71
     babys
    0.71
    Act Density 0.273%

    No Known Activations