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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various activities, challenges, and actions in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    topics related to financial misconduct and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CG
    -0.67
    Spoiler
    -0.65
    iann
    -0.64
    aed
    -0.64
    Reloaded
    -0.63
    hematically
    -0.61
    lein
    -0.60
    desktop
    -0.60
    Bed
    -0.59
    Plug
    -0.59
    POSITIVE LOGITS
     alike
    1.57
     respectively
    1.39
     abound
    0.82
    SPONSORED
    0.77
     attRot
    0.76
     thereof
    0.76
     among
    0.73
    hips
    0.71
     etc
    0.71
     amongst
    0.68
    Act Density 0.618%

    No Known Activations