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

    Neuronpedia

    INDEX
    Explanations

    French pronouns and verbs related to self-reference or direct interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.63
     snippetHide
    -0.59
    endphp
    -0.54
     InputDecoration
    -0.50
     صوتيه
    -0.47
    Jereo
    -0.47
    verwijspagina
    -0.45
    ManagedBean
    -0.44
     oprot
    -0.44
    chowa
    -0.43
    POSITIVE LOGITS
    把它
    0.57
    把他
    0.54
    把她
    0.46
     lhes
    0.45
     idéia
    0.45
    将他
    0.42
    将其
    0.42
    これを
    0.40
    将她
    0.39
    作り方
    0.39
    Act Density 0.155%

    No Known Activations