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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of abandonment or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èħ
    -0.15
    ostat
    -0.15
     kept
    -0.14
    igy
    -0.14
    orrect
    -0.14
    ubat
    -0.14
    maj
    -0.13
    iry
    -0.13
    hub
    -0.13
    سÙĦ
    -0.13
    POSITIVE LOGITS
     feeling
    0.23
     behind
    0.21
     Behind
    0.17
    à¥Įà¤Ĥ
    0.16
    vens
    0.16
     impression
    0.16
     stranded
    0.16
     open
    0.16
     wondering
    0.15
    Behind
    0.15
    Act Density 0.053%

    No Known Activations