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

    Neuronpedia

    INDEX
    Explanations

    indications of emotional responses, particularly panic and its effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    they
    -0.55
    Their
    -0.52
    เค้า
    -0.49
    They
    -0.49
     they
    -0.47
    РОВ
    -0.46
     They
    -0.46
    Они
    -0.46
     Their
    -0.46
     Mereka
    -0.45
    POSITIVE LOGITS
     myself
    0.96
    自分は
    0.79
     my
    0.79
    的我
    0.70
     meus
    0.70
    自分が
    0.69
     me
    0.66
    帖最后由
    0.64
    myself
    0.64
     personnelle
    0.64
    Act Density 0.575%

    No Known Activations