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

    Neuronpedia

    INDEX
    Explanations

    phrases that express concern for well-being and safety, particularly in relation to individuals and families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to self-preservation, protection, and defense

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    geoning
    -0.70
     Gleaming
    -0.68
    代
    -0.65
    Thumbnail
    -0.61
    ãģ®éŃĶ
    -0.61
     guiActiveUnfocused
    -0.61
    VERTISEMENT
    -0.60
     Wrest
    -0.59
     Reconstruction
    -0.58
    auder
    -0.58
    POSITIVE LOGITS
     others
    1.16
     yours
    0.93
     theirs
    0.86
     Others
    0.84
     anyone
    0.82
     ours
    0.78
     strangers
    0.76
     mates
    0.76
     hers
    0.74
     peers
    0.74
    Act Density 0.126%

    No Known Activations