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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fall" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyn
    -0.17
    emoc
    -0.16
    elin
    -0.16
    alon
    -0.15
    elan
    -0.15
    yle
    -0.15
    eland
    -0.14
    es
    -0.14
    ÑĢ
    -0.14
    roker
    -0.14
    POSITIVE LOGITS
     victim
    0.29
     asleep
    0.27
     Victim
    0.25
    acy
    0.25
    acies
    0.24
     prey
    0.23
    victim
    0.23
     into
    0.22
     foul
    0.20
     Fell
    0.19
    Act Density 0.036%

    No Known Activations