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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal or violent actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the definite article "the" in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.77
    osphere
    -0.76
    thood
    -0.74
    âĦ¢:
    -0.74
    ceive
    -0.74
    usa
    -0.73
    Boost
    -0.71
     âĢº
    -0.71
    cially
    -0.70
    imi
    -0.70
    POSITIVE LOGITS
     youngest
    1.13
     latter
    1.08
    odore
    1.06
    resa
    1.06
     slightest
    0.98
     remainder
    0.97
     oldest
    0.95
    oret
    0.94
     occupants
    0.93
     whereabouts
    0.93
    Act Density 0.516%

    No Known Activations