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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reclaiming or retrieval

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of returning or bringing something back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achi
    -0.99
     Ich
    -0.94
    ECT
    -0.92
     TAMADRA
    -0.89
    CE
    -0.88
    Sense
    -0.84
     Phill
    -0.83
    Phill
    -0.82
     Collins
    -0.78
     Phillips
    -0.78
    POSITIVE LOGITS
    BACK
    1.17
     BACK
    1.16
    back
    1.14
     backs
    1.13
     back
    1.08
     Back
    1.03
    backs
    1.01
     backed
    0.97
     backward
    0.97
     backwards
    0.94
    Act Density 0.239%

    No Known Activations