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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onda
    -0.14
     latest
    -0.13
    issy
    -0.13
    лиж
    -0.13
     constructors
    -0.13
     ÐĵаÑĢ
    -0.13
    aled
    -0.13
    á»±a
    -0.13
    alaria
    -0.12
     åĶ
    -0.12
    POSITIVE LOGITS
     friendly
    0.25
     Friendly
    0.22
     friend
    0.22
    friendly
    0.21
     life
    0.21
    åıĭ
    0.21
     friendships
    0.21
     encounter
    0.20
     encounters
    0.20
     FRIEND
    0.20
    Act Density 0.104%

    No Known Activations