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

    Neuronpedia

    INDEX
    Explanations

    words related to personal beliefs, actions, and interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal insecurity and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leck
    -0.67
    helps
    -0.60
    bur
    -0.59
    ONSORED
    -0.59
    geist
    -0.59
    herry
    -0.59
    eele
    -0.59
    ullah
    -0.58
     sidx
    -0.58
    itual
    -0.58
    POSITIVE LOGITS
     myself
    1.23
     thee
    0.94
     THEM
    0.84
     yours
    0.83
     them
    0.81
     ourselves
    0.78
     ya
    0.77
     YOU
    0.76
     you
    0.75
     my
    0.74
    Act Density 1.045%

    No Known Activations