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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate transitions or connections in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.17
    thy
    -0.16
    ÑıÑģÑĮ
    -0.16
    aits
    -0.15
     Slip
    -0.15
    udge
    -0.15
    ij¸
    -0.14
    uti
    -0.14
    awah
    -0.14
    ayas
    -0.14
    POSITIVE LOGITS
     forth
    0.36
     us
    0.31
     up
    0.24
    ToFront
    0.21
    forth
    0.21
     about
    0.21
     tears
    0.20
     into
    0.19
     rise
    0.19
     along
    0.17
    Act Density 0.024%

    No Known Activations