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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to being at risk or susceptible to harm

    oai_token-act-pair · gpt-3.5-turbo

    references to vulnerability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.76
    zos
    -0.75
    tein
    -0.73
    OTO
    -0.69
    aster
    -0.68
    inth
    -0.68
    ALSE
    -0.67
    flu
    -0.65
    ool
    -0.63
    oret
    -0.63
    POSITIVE LOGITS
     vulnerable
    1.06
     vulner
    0.90
    ulnerable
    0.87
     adolesc
    0.84
     victims
    0.81
     vulnerability
    0.77
    ansas
    0.76
     bystanders
    0.73
     vulnerabilities
    0.71
     tenants
    0.71
    Act Density 0.021%

    No Known Activations