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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewood
    -0.15
    alue
    -0.15
     backgrounds
    -0.14
    atoria
    -0.14
    ltk
    -0.14
     koneÄį
    -0.14
    nder
    -0.14
    pra
    -0.14
    DDL
    -0.14
    lsa
    -0.13
    POSITIVE LOGITS
     footsteps
    0.45
     lead
    0.41
    lead
    0.32
     path
    0.31
     Lead
    0.31
     leads
    0.30
     steps
    0.29
     closely
    0.29
    Lead
    0.29
     trail
    0.29
    Act Density 0.090%

    No Known Activations