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

    Neuronpedia

    INDEX
    Explanations

    the concept of proximity or becoming nearer to something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     }}>
    -0.60
     nearby
    -0.60
    __":
    -0.53
     }}">
    -0.52
     neighbouring
    -0.52
    Thread
    -0.51
     ibang
    -0.51
    }`).
    -0.51
    "]/
    -0.51
    ']").
    -0.51
    POSITIVE LOGITS
     closer
    1.34
    closer
    1.15
     Closer
    1.12
    Closer
    0.96
     charged
    0.95
     Charged
    0.80
     nearer
    0.80
     Breakdown
    0.79
    Breakdown
    0.75
    breakdown
    0.74
    Act Density 0.091%

    No Known Activations