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

    Neuronpedia

    INDEX
    Explanations

    phrases related to directives or commands

    oai_token-act-pair · gpt-3.5-turbo

    titles and phrases related to themes of support and resilience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UC
    -0.90
    bub
    -0.84
    compan
    -0.81
    jet
    -0.74
    crit
    -0.73
    mini
    -0.72
    lets
    -0.72
    stim
    -0.71
    quant
    -0.70
    bet
    -0.70
    POSITIVE LOGITS
     Thrones
    0.90
     Silence
    0.80
     Mormon
    0.77
     Mormonism
    0.77
    Ħ¢
    0.75
     Ashes
    0.75
     Annotations
    0.74
     Darkness
    0.73
     Influence
    0.72
     Records
    0.71
    Act Density 0.133%

    No Known Activations