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

    Neuronpedia

    INDEX
    Explanations

    phrases related to career opportunities and job applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     learnt
    -0.17
     Learned
    -0.16
     proced
    -0.15
    zent
    -0.15
    iller
    -0.15
    amen
    -0.15
     PROVIDED
    -0.14
     learned
    -0.14
     Cum
    -0.14
     kut
    -0.14
    POSITIVE LOGITS
     pop
    0.26
    pop
    0.25
     popped
    0.23
    Pop
    0.21
     Pop
    0.21
     popping
    0.21
    -pop
    0.20
    .pop
    0.20
    _pop
    0.19
     why
    0.18
    Act Density 0.163%

    No Known Activations