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

    Neuronpedia

    INDEX
    Explanations

    phrases related to traumatic or challenging experiences

    oai_token-act-pair · gpt-3.5-turbo

    words related to affirmation or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£ıç
    -0.89
    REDACTED
    -0.73
    Spoiler
    -0.69
     Lights
    -0.68
     Rasm
    -0.67
     spared
    -0.67
    å¥
    -0.66
     pandemonium
    -0.65
     Tribunal
    -0.64
    NetMessage
    -0.64
    POSITIVE LOGITS
    atively
    1.17
    irm
    1.12
    ative
    1.07
    ament
    1.01
    atives
    0.95
    aton
    0.93
    ware
    0.86
    irms
    0.85
    anyahu
    0.85
    atory
    0.85
    Act Density 0.026%

    No Known Activations