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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing challenges and complexities in personal or emotional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doomed
    -0.16
     astonished
    -0.15
    afil
    -0.15
     stunned
    -0.14
    anie
    -0.14
    518
    -0.14
     dob
    -0.14
    imb
    -0.14
     horrified
    -0.14
    ecast
    -0.13
    POSITIVE LOGITS
     dem
    0.27
     nerve
    0.25
     dis
    0.24
     liber
    0.23
     isol
    0.23
     foreign
    0.20
     wearing
    0.20
     draining
    0.20
     mort
    0.20
     distress
    0.19
    Act Density 0.265%

    No Known Activations