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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achieving success or hitting targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spesa
    -0.57
    Flux
    -0.57
     généraux
    -0.56
     Flux
    -0.54
    OSSARY
    -0.53
    hésite
    -0.53
    alej
    -0.52
     bruge
    -0.51
     hâte
    -0.50
     fluxes
    -0.49
    POSITIVE LOGITS
     hitting
    1.52
     hit
    1.45
     hits
    1.39
    hitting
    1.36
     knock
    1.32
     knocked
    1.31
    hit
    1.24
     knocks
    1.24
     smack
    1.23
     strikes
    1.21
    Act Density 0.169%

    No Known Activations