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

    Neuronpedia

    INDEX
    Explanations

    words related to extraction or conversion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extraction and transformation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resp
    -0.79
    zl
    -0.78
    ells
    -0.78
    roc
    -0.77
    ighth
    -0.75
    itude
    -0.74
    hest
    -0.73
    itudes
    -0.73
    icial
    -0.72
    eva
    -0.72
    POSITIVE LOGITS
     process
    0.91
     prevention
    0.87
     mechanism
    0.79
     scheme
    0.79
     techniques
    0.79
     technique
    0.78
     derby
    0.78
     methods
    0.76
     procedure
    0.75
     spree
    0.74
    Act Density 0.224%

    No Known Activations