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

    Neuronpedia

    INDEX
    Explanations

    words related to actions of removing or retrieving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the action of removing or taking something out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ���
    -0.74
    staking
    -0.74
    ��
    -0.74
    externalActionCode
    -0.69
    ita
    -0.68
    MQ
    -0.65
    terday
    -0.65
    ãĤ´ãĥ³
    -0.63
    IAS
    -0.63
    otion
    -0.62
    POSITIVE LOGITS
     distractions
    0.85
     some
    0.83
     scraps
    0.82
     bits
    0.79
     chunks
    0.79
     portions
    0.79
     weeds
    0.77
     whatever
    0.77
     any
    0.76
     tons
    0.76
    Act Density 0.175%

    No Known Activations