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

    Neuronpedia

    INDEX
    Explanations

    instances where something is physically dropping or being dropped

    oai_token-act-pair · gpt-3.5-turbo

    references to dropping or abandoning something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Administ
    -0.73
    SELECT
    -0.69
    ALE
    -0.68
    wh
    -0.65
    FORMATION
    -0.63
    âĸ¬
    -0.63
    GY
    -0.63
    NEY
    -0.62
    Supported
    -0.62
    CLA
    -0.62
    POSITIVE LOGITS
     bombshell
    0.98
     bombs
    0.81
     hints
    0.78
     inhib
    0.73
     punches
    0.73
     sidx
    0.71
     leaflets
    0.70
     Tow
    0.70
     pounds
    0.69
     torches
    0.68
    Act Density 0.097%

    No Known Activations