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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions and behaviors, especially negative ones

    oai_token-act-pair · gpt-3.5-turbo

    themes related to emotional processing and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.94
    phalt
    -0.86
    çīĪ
    -0.85
    prints
    -0.84
    atel
    -0.77
    aughtered
    -0.77
     Forestry
    -0.70
     Bullets
    -0.70
     GOODMAN
    -0.69
     Manufacturer
    -0.68
    POSITIVE LOGITS
     narciss
    1.41
     narcissistic
    1.33
     psychopath
    1.31
     behaviors
    1.27
     subconscious
    1.27
     personality
    1.27
     behaviours
    1.23
     depressive
    1.22
     interpersonal
    1.22
     pathological
    1.20
    Act Density 0.974%

    No Known Activations