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

    Neuronpedia

    INDEX
    Explanations

    phrases related to solitude and personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.59
    ACTIVE
    -0.50
    Damaged
    -0.48
     incendie
    -0.48
    ValueStyle
    -0.48
    utilisons
    -0.47
     active
    -0.47
    basa
    -0.46
    Active
    -0.46
    active
    -0.46
    POSITIVE LOGITS
     solitude
    1.19
     privacy
    1.12
     isolation
    1.08
     isolated
    1.06
     Alone
    1.01
     quiet
    1.00
     secluded
    1.00
     alone
    0.99
    alone
    0.97
    isolated
    0.97
    Act Density 0.214%

    No Known Activations