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

    Neuronpedia

    INDEX
    Explanations

    references to solitude or being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anzu
    -0.65
    forName
    -0.65
     незавершена
    -0.64
     Mandi
    -0.63
    jetas
    -0.62
    település
    -0.62
    errHandler
    -0.62
    ypeł
    -0.60
     Versicher
    -0.59
    uthorized
    -0.58
    POSITIVE LOGITS
     alone
    0.96
     Alone
    0.95
     stuck
    0.79
     ALONE
    0.79
    Alone
    0.77
    alone
    0.65
     adhered
    0.64
     merit
    0.64
     âgées
    0.64
     adhering
    0.60
    Act Density 0.049%

    No Known Activations