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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical discussions about "memory safety" in programming

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to programming challenges or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.96
    itud
    -0.75
    unc
    -0.74
    cock
    -0.72
    names
    -0.71
    lehem
    -0.71
    anamo
    -0.70
    unct
    -0.69
    reality
    -0.69
    alore
    -0.69
    POSITIVE LOGITS
    eral
    0.72
     Asuka
    0.67
     Opinion
    0.67
    Accessory
    0.63
     Silva
    0.63
     Hardy
    0.62
     Signature
    0.60
     Shiny
    0.60
     Viol
    0.59
     Happiness
    0.59
    Act Density 0.000%

    No Known Activations