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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their perceived characteristics or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.82
    natureconservancy
    -0.77
     intrusion
    -0.71
    Role
    -0.68
     glove
    -0.68
     inconsistency
    -0.66
     timeline
    -0.66
     instr
    -0.65
     clause
    -0.65
     hospitality
    -0.65
    POSITIVE LOGITS
    icons
    0.88
     realizes
    0.80
     suffers
    0.79
     faces
    0.76
    mates
    0.74
     realise
    0.73
    bers
    0.71
     understands
    0.71
     realised
    0.70
    herty
    0.70
    Act Density 0.184%

    No Known Activations