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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss of control or being out of touch with reality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a disconnection or lack of control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incial
    -0.79
    Ń·
    -0.73
    nai
    -0.73
    agher
    -0.72
    arnaev
    -0.71
    utical
    -0.70
    ioxide
    -0.70
    ains
    -0.70
    ellow
    -0.69
    ruary
    -0.68
    POSITIVE LOGITS
     surprises
    0.73
    alus
    0.72
     distractions
    0.69
     situations
    0.68
    Ø©
    0.67
     misconceptions
    0.63
     boredom
    0.63
     generators
    0.62
     audits
    0.61
     considerations
    0.60
    Act Density 0.055%

    No Known Activations