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

    Neuronpedia

    INDEX
    Explanations

    editor's notes in texts

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating ownership or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yz
    -0.81
    ENN
    -0.78
    ĪĴ
    -0.74
    USD
    -0.71
    GBT
    -0.70
    ACP
    -0.70
    ĸļ
    -0.70
    western
    -0.69
    esm
    -0.66
    facts
    -0.66
    POSITIVE LOGITS
     Wife
    0.84
     Creed
    0.83
     remorse
    0.81
     grasp
    0.81
     paradise
    0.80
     veto
    0.79
     own
    0.78
    haw
    0.77
     lounge
    0.77
     Guild
    0.76
    Act Density 0.079%

    No Known Activations