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

    Neuronpedia

    INDEX
    Explanations

    instances of accountability and self-centered behavior in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klopp
    -0.16
     hamm
    -0.15
    760
    -0.15
     Adaptive
    -0.14
    ött
    -0.14
    hatt
    -0.14
    òng
    -0.14
     mari
    -0.14
    jom
    -0.13
    IPA
    -0.13
    POSITIVE LOGITS
     Son
    0.32
     GH
    0.27
    Son
    0.27
    GH
    0.25
     Carly
    0.23
     Dante
    0.22
     Corinth
    0.22
     Mob
    0.21
     mob
    0.21
     Spin
    0.21
    Act Density 0.002%

    No Known Activations