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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consequences and risks of actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbs
    -0.15
     vej
    -0.15
     Lum
    -0.15
    urance
    -0.14
     lum
    -0.14
    ullo
    -0.14
     Setter
    -0.14
     éĿ
    -0.13
    anas
    -0.13
    iams
    -0.13
    POSITIVE LOGITS
     rebound
    0.26
     rebounds
    0.26
     back
    0.25
     backlash
    0.23
     bite
    0.22
     bo
    0.21
    -back
    0.19
     BACK
    0.19
     biting
    0.19
    Back
    0.19
    Act Density 0.168%

    No Known Activations