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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional responses and personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.70
     때문
    -0.66
    NUMX
    -0.65
     Majefty
    -0.63
     sahiptir
    -0.59
     Gump
    -0.58
    로운
    -0.56
     fupp
    -0.55
     acepción
    -0.55
     الحره
    -0.55
    POSITIVE LOGITS
     تانيه
    0.60
    Bibliografia
    0.59
    verwijspagina
    0.55
     Howe
    0.55
    GrantedAuthority
    0.54
    erals
    0.53
    Hentet
    0.53
    adget
    0.52
    ïti
    0.51
    Посилання
    0.50
    Act Density 0.127%

    No Known Activations