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

    Neuronpedia

    INDEX
    Explanations

    phrases related to utilizing resources or making connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cas
    -0.74
    numbered
    -0.72
    bott
    -0.71
    aughtered
    -0.70
    shake
    -0.70
    je
    -0.67
    guards
    -0.66
    stad
    -0.66
    iatus
    -0.65
    occup
    -0.65
    POSITIVE LOGITS
     strengths
    1.14
     energies
    1.12
     talents
    0.99
     intuition
    0.98
     ingenuity
    0.97
     imagination
    0.95
     expertise
    0.92
     resources
    0.92
     latent
    0.89
     instincts
    0.87
    Act Density 0.109%

    No Known Activations