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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following or tracking in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     igenom
    -0.60
    szönöm
    -0.60
     pensent
    -0.60
     Schein
    -0.57
    empêcher
    -0.56
    ielles
    -0.55
     sitzen
    -0.55
     AttributeSet
    -0.54
    DoesNotExist
    -0.54
    ]--;
    -0.53
    POSITIVE LOGITS
     followed
    1.37
     follow
    1.34
     Followed
    1.29
    followed
    1.26
     follows
    1.26
     Follows
    1.24
     FOLLOW
    1.23
     Follow
    1.17
    follow
    1.16
    Followed
    1.14
    Act Density 0.316%

    No Known Activations