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

    Neuronpedia

    INDEX
    Explanations

    phrases that evoke strong emotional responses or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ór
    -0.16
    iro
    -0.15
    akeup
    -0.15
     Lonely
    -0.14
    opath
    -0.14
     annoyed
    -0.14
     éĹ
    -0.14
     znam
    -0.14
     irritated
    -0.14
     bored
    -0.14
    POSITIVE LOGITS
     speech
    0.40
    speech
    0.35
     Speech
    0.34
     aw
    0.33
    Speech
    0.33
     awe
    0.31
     gas
    0.29
     dumb
    0.29
     spell
    0.29
     jaw
    0.29
    Act Density 0.272%

    No Known Activations