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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with proximity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    олж
    -0.12
    егоÑĢ
    -0.12
    okoj
    -0.12
    amu
    -0.12
     {}č↵
    -0.12
    ovice
    -0.12
    овÑĸд
    -0.11
    ymm
    -0.11
    redient
    -0.11
    alion
    -0.11
    POSITIVE LOGITS
     close
    0.95
    close
    0.79
     closer
    0.77
     closest
    0.75
    -close
    0.74
     near
    0.73
     Close
    0.73
     CLOSE
    0.73
     clos
    0.70
     nearer
    0.69
    Act Density 0.443%

    No Known Activations