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

    Neuronpedia

    INDEX
    Explanations

    references to neo-Nazi groups

    oai_token-act-pair · gpt-3.5-turbo

    references to neo-Nazi ideology and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.92
    =-=-=-=-
    -0.78
    Medium
    -0.77
    Issue
    -0.77
    ANGE
    -0.75
    hips
    -0.73
    perature
    -0.72
    loo
    -0.71
    ingham
    -0.71
    room
    -0.71
    POSITIVE LOGITS
     neo
    1.05
     Neo
    0.80
     nihil
    0.77
     fascist
    0.75
    emer
    0.75
    igen
    0.72
     supremacist
    0.71
     mascul
    0.69
    ge
    0.69
    utsche
    0.69
    Act Density 0.005%

    No Known Activations