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

    Neuronpedia

    INDEX
    Explanations

    geographical locations, especially those related to rivers and forests

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corbyn
    -0.80
    byn
    -0.79
     Isis
    -0.75
     JS
    -0.69
     Gideon
    -0.68
    foundation
    -0.67
     Kushner
    -0.67
     Sheikh
    -0.66
     Clash
    -0.64
     blacklist
    -0.63
    POSITIVE LOGITS
    �
    4.29
     �
    3.18
    ��
    2.99
    .�
    2.89
    ���
    2.70
    ����
    2.41
    \'
    1.96
    ´
    1.94
     ��������
    1.79
    `
    1.76
    Act Density 0.010%

    No Known Activations