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

    Neuronpedia

    INDEX
    Explanations

    words related to security and insecurity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insecurity and unstable situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estone
    -0.82
    ague
    -0.80
    oran
    -0.72
    eric
    -0.72
    kay
    -0.71
    meric
    -0.70
    eree
    -0.70
    ieu
    -0.69
    resh
    -0.69
    estones
    -0.68
    POSITIVE LOGITS
     insecure
    0.89
     adolesc
    0.88
     insecurity
    0.88
     comprom
    0.79
    ariat
    0.77
    urities
    0.76
     patched
    0.72
     metic
    0.71
     masculinity
    0.70
    aged
    0.70
    Act Density 0.009%

    No Known Activations