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

    Neuronpedia

    INDEX
    Explanations

    the names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to various subjects or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.86
    LEASE
    -0.72
    Magikarp
    -0.70
    è£ħ
    -0.67
    REDACTED
    -0.66
     sidx
    -0.66
    eers
    -0.66
    20439
    -0.65
     thereto
    -0.64
    /-
    -0.63
    POSITIVE LOGITS
    oslav
    0.83
    abit
    0.82
    orius
    0.82
    adian
    0.81
    hett
    0.80
    adier
    0.79
    sey
    0.78
    anyahu
    0.78
    imar
    0.77
    wich
    0.76
    Act Density 0.194%

    No Known Activations