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

    Neuronpedia

    INDEX
    Explanations

    terms related to social interaction and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esistenza
    -0.44
     rencana
    -0.35
     indipendente
    -0.32
     enkel
    -0.31
     hjelpe
    -0.31
     possible
    -0.31
     unfair
    -0.30
    impianto
    -0.30
     geçi
    -0.30
     zbior
    -0.30
    POSITIVE LOGITS
     extro
    0.75
     friendliness
    0.71
     smiles
    0.66
     smiling
    0.62
     friendly
    0.61
    smiling
    0.61
     sociable
    0.61
     charisma
    0.60
     amiable
    0.60
    MLLoader
    0.60
    Act Density 0.016%

    No Known Activations