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

    Neuronpedia

    INDEX
    Explanations

    verbs related to conditions or states of being that indicate influence or dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licit
    -0.15
     cher
    -0.15
     /
    -0.15
     fraught
    -0.14
     toler
    -0.14
    neau
    -0.14
    ead
    -0.14
     for
    -0.14
     alone
    -0.14
    earch
    -0.14
    POSITIVE LOGITS
     influenced
    0.35
     dependent
    0.34
    dependent
    0.30
     depend
    0.29
     affected
    0.29
    affected
    0.29
     determined
    0.28
     driven
    0.27
     depends
    0.24
    depends
    0.24
    Act Density 0.171%

    No Known Activations