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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inserting or moving items into a specified location

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing the action of moving something into a particular place or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.81
    zai
    -0.74
     fortun
    -0.72
    gang
    -0.67
     insulted
    -0.65
    mand
    -0.64
     disapproval
    -0.63
     intimid
    -0.62
     reluct
    -0.62
     slowdown
    -0.62
    POSITIVE LOGITS
     adulthood
    0.94
    itialized
    0.85
    pload
    0.80
     orbit
    0.79
    jected
    0.79
    eligible
    0.72
     Preferences
    0.71
    flow
    0.70
     Radius
    0.69
    flows
    0.67
    Act Density 0.068%

    No Known Activations