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

    Neuronpedia

    INDEX
    Explanations

    emotional dynamics and dependency in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .IDENTITY
    -0.15
    ãģ¤ãģ¶
    -0.14
     retire
    -0.14
    ostel
    -0.14
    eken
    -0.14
    ·æĸ°
    -0.14
    ëįķ
    -0.14
     defeat
    -0.13
     inspir
    -0.13
    (tuple
    -0.13
    POSITIVE LOGITS
     ghost
    0.24
    Ghost
    0.23
     Ghost
    0.22
     hurt
    0.21
     friendship
    0.21
    ghost
    0.21
     toxicity
    0.20
     manip
    0.20
     Toxic
    0.20
    Distance
    0.19
    Act Density 0.623%

    No Known Activations