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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Love," indicating a focus on themes of love in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mybatisplus
    -0.18
    íĦ´
    -0.16
    ness
    -0.16
    webtoken
    -0.16
    sis
    -0.16
    onder
    -0.15
    xA
    -0.15
    ÑĢава
    -0.15
    éĻ¢
    -0.15
    sk
    -0.15
    POSITIVE LOGITS
    joy
    0.22
     Actually
    0.22
    leen
    0.21
    able
    0.19
    less
    0.19
     Potion
    0.19
    146
    0.19
    craft
    0.18
    Actually
    0.17
     triangle
    0.17
    Act Density 0.011%

    No Known Activations