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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violence and conflict

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to violence and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.78
    paren
    -0.77
    pring
    -0.72
    uart
    -0.71
    ource
    -0.71
    abase
    -0.71
    arten
    -0.70
    earcher
    -0.69
    leans
    -0.69
    irmation
    -0.67
    POSITIVE LOGITS
     havoc
    0.98
     retribution
    0.94
     assaults
    0.93
     harassing
    0.92
     murders
    0.92
     murdering
    0.92
     vicious
    0.89
     intimidation
    0.89
     treason
    0.88
     thugs
    0.88
    Act Density 0.979%

    No Known Activations