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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data processing and management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data processes and collection activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥī
    -0.79
    zl
    -0.69
     recol
    -0.66
    SN
    -0.65
    {"
    -0.64
    DN
    -0.63
    SPONSORED
    -0.62
     Rove
    -0.61
    shown
    -0.60
     Ago
    -0.59
    POSITIVE LOGITS
     extraord
    0.82
    itaire
    0.82
    glers
    0.80
    uction
    0.79
     prevention
    0.79
     advocate
    0.78
    itives
    0.76
     scams
    0.73
     algorithm
    0.72
     campaigner
    0.72
    Act Density 0.542%

    No Known Activations