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

    Neuronpedia

    INDEX
    Explanations

    repeated conjunctions and affirming phrases in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.75
     ddelweddau
    -0.69
    줌
    -0.61
     itſelf
    -0.61
     myſelf
    -0.61
    ArrowToggle
    -0.60
    weakSelf
    -0.60
    ('');
    -0.59
     msglen
    -0.58
    ſelves
    -0.57
    POSITIVE LOGITS
    And
    0.74
     it
    0.69
     everybody
    0.68
     you
    0.67
     And
    0.66
     we
    0.64
     they
    0.63
     if
    0.61
     everyone
    0.60
    commit
    0.59
    Act Density 0.319%

    No Known Activations